© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 14573
    Prev
    Next
    INDEX
    Explanations

    technical terms and abbreviations

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     schlug
    -0.96
    ay
    -0.96
    ころ
    -0.95
    if
    -0.93
     gewann
    -0.91
    他們
    -0.91
    確實
    -0.90
    ѝ
    -0.89
     …
    -0.88
    pay
    -0.86
    POSITIVE LOGITS
    狛
    1.18
    brtc
    1.16
     saksi
    1.13
    <bos>
    1.13
    儚
    1.08
    掟
    1.05
    skjaer
    1.04
    古屋
    1.04
    睨
    1.03
    鳥居
    1.02
    Activations Density 0.051%

    No Known Activations