© 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. 26811
    Prev
    Next
    INDEX
    Explanations

    key: value assignments

    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
    つづく
    -1.34
    mazda
    -1.19
     you
    -1.19
    おわりに
    -1.18
    さあ
    -1.16
    ％
    -1.14
     ?
    -1.13
    無し
    -1.11
     any
    -1.09
     create
    -1.07
    POSITIVE LOGITS
    がありますが
    1.38
    を持ち
    1.32
    があるので
    1.30
    などは
    1.24
    ってこと
    1.21
     поэтому
    1.19
    <bos>
    1.18
    などと
    1.18
     continúas
    1.16
    という感じ
    1.14
    Activations Density 0.001%

    No Known Activations