© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 127655
    Prev
    Next
    INDEX
    Explanations

    public class declaration

    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
     estadounid
    -2.13
    ܖ
    -2.05
    </em>
    -1.98
    놋
    -1.86
     parachoque
    -1.86
    鶿
    -1.84
    Ꮸ
    -1.84
    </h2>
    -1.83
    
    -1.82
    ꯵
    -1.78
    POSITIVE LOGITS
     and
    2.20
     or
    2.16
     in
    2.16
     —
    2.11
    1
    2.03
     which
    1.95
    ";
    1.91
     by
    1.78
     –
    1.76
     whereby
    1.65
    Activations Density 0.043%

    No Known Activations