© 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. 22-GEMMASCOPE-RES-131K
    7. 64929
    Prev
    Next
    INDEX
    Explanations

    near type import worker list

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

    the presence of numeric literals (numbers, percentages, or other digit‐containing tokens) in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    zdroj
    -1.55
    mô
    -1.50
     anún
    -1.48
    rechten
    -1.47
    ̳
    -1.46
     parlar
    -1.46
    וּ
    -1.46
     coreano
    -1.43
    middag
    -1.41
     accompagner
    -1.38
    POSITIVE LOGITS
     analysis
    1.67
     two
    1.44
     we
    1.41
     other
    1.38
     find
    1.38
     analyzing
    1.28
     others
    1.27
    textnormal
    1.27
     ocurre
    1.26
     this
    1.25
    Activations Density 0.013%

    No Known Activations