© 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. 10-GEMMASCOPE-RES-131K
    7. 67989
    Prev
    Next
    INDEX
    Explanations

    or

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

    This neuron detects the plural “-s” suffix marking plural nouns.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    .
    -2.53
    5
    -2.36
    1
    -2.34
    7
    -2.34
     protetor
    -2.27
    ."
    -2.05
    4
    -1.97
    他们在
    -1.96
    6
    -1.95
    9
    -1.95
    POSITIVE LOGITS
    или
    2.59
    明け
    1.75
    }$,
    1.72
    または
    1.66
    olução
    1.63
    genheiten
    1.61
    ulsar
    1.60
    ى
    1.59
    zystać
    1.59
    Или
    1.58
    Activations Density 0.026%

    No Known Activations