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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 12231
    Prev
    Next
    INDEX
    Explanations

    Q:

    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
     this
    -1.06
     the
    -1.02
     that
    -0.93
    Scene
    -0.88
    I
    -0.86
    记者
    -0.86
    而
    -0.85
    Ÿ
    -0.85
     sebagaimana
    -0.84
    резать
    -0.84
    POSITIVE LOGITS
    してみると
    1.28
    Hilsen
    1.18
     soulign
    1.17
    Ещё
    1.14
    勠
    1.13
    Imgur
    1.13
    Genial
    1.11
    Cordial
    1.11
    Вариан
    1.11
     nuevamente
    1.11
    Activations Density 0.004%

    No Known Activations