© 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. 22-GEMMASCOPE-RES-131K
    7. 72749
    Prev
    Next
    INDEX
    Explanations

    code, names, and structured text

    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
    łasz
    -0.92
     enough
    -0.82
     UnityEditor
    -0.80
     maxY
    -0.80
    convertTo
    -0.79
     maturity
    -0.78
    Export
    -0.77
    сть
    -0.76
    End
    -0.76
     使用
    -0.76
    POSITIVE LOGITS
    Somalia
    0.97
    puesto
    0.88
    Saison
    0.88
    ukų
    0.88
    Leírás
    0.86
    Teatro
    0.85
     espé
    0.85
    }?>
    0.84
    Conception
    0.83
    bilden
    0.82
    Activations Density 0.000%

    No Known Activations