© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 64249
    Prev
    Next
    INDEX
    Explanations

    enclosing or engulfing

    np_acts-logits-general · gemini-2.5-flash-lite

    phrases where "of the" or similar preposition phrases appear in academic text.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    This neuron detects common English prepositional‐article phrase patterns (e.g. "in the", "of the", "after removal of the").

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     получили
    -0.85
     oppressed
    -0.84
     APPE
    -0.84
    琊
    -0.75
    変わり
    -0.74
    orul
    -0.73
    ANCI
    -0.73
    落ち
    -0.73
     Adds
    -0.73
     blessé
    -0.72
    POSITIVE LOGITS
     sponsoring
    2.16
     underlying
    2.13
     supporting
    1.97
     controlling
    1.70
     enclosing
    1.66
    underlying
    1.66
     presiding
    1.65
     initiating
    1.57
     supervising
    1.55
     hosting
    1.52
    Activations Density 0.294%

    No Known Activations