© 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. 8387
    Prev
    Next
    INDEX
    Explanations

    must be

    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
    </td>
    -1.72
    %',
    -1.66
    fourths
    -1.65
    }$,
    -1.58
     This
    -1.58
     jego
    -1.57
     by
    -1.52
    inaison
    -1.46
     selben
    -1.45
     asociado
    -1.45
    POSITIVE LOGITS
    <bos>
    1.52
     edelstahl
    1.43
     hintergrund
    1.38
    曏
    1.36
     brasile
    1.36
     baumwolle
    1.34
    用户信息
    1.34
     colch
    1.32
     odpowiedzi
    1.31
    Confused
    1.30
    Activations Density 0.041%

    No Known Activations