© 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. 84620
    Prev
    Next
    INDEX
    Explanations

    aggressive behavior

    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_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
    焄
    -3.22
    豋
    -3.09
    猻
    -3.06
    Ⲉ
    -2.91
    ?’
    -2.70
    ៚
    -2.64
    }$.
    -2.53
     optimized
    -2.45
    ﮕ
    -2.42
     incorporates
    -2.34
    POSITIVE LOGITS
    .
    2.31
     Когда
    2.30
     就是
    2.23
     undoubted
    2.22
     Mientras
    2.22
     Два
    2.14
    久し
    2.05
    已經
    2.05
    ↵
    2.03
     IMPORTANT
    2.03
    Activations Density 0.003%

    No Known Activations