© 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. 21995
    Prev
    Next
    INDEX
    Explanations

    words following `of`

    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
     Anſ
    -2.30
     the
    -2.28
    ⸂
    -2.23
    ⸥
    -2.20
    皤
    -2.16
    撄
    -2.11
    饪
    -2.08
    ⚣
    -2.06
    柃
    -2.06
     nul
    -2.06
    POSITIVE LOGITS
     in
    2.52
    </h2>
    2.52
     from
    2.25
    }
    2.23
     become
    2.20
     with
    2.11
     incredible
    2.08
     around
    2.03
     participado
    2.03
     about
    2.02
    Activations Density 0.105%

    No Known Activations