© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 101153
    Prev
    Next
    INDEX
    Explanations

    perspective

    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
     be
    -3.55
    }
    -2.89
     This
    -2.86
     was
    -2.81
    derdag
    -2.72
    眼睛
    -2.42
     économie
    -2.42
     télécommande
    -2.36
    </i>
    -2.34
     Use
    -2.33
    POSITIVE LOGITS
    ”،
    3.77
    脔
    3.33
    ⢓
    2.92
    ⃢
    2.70
    阄
    2.69
    ༀ
    2.69
    詒
    2.66
    菝
    2.64
    髫
    2.63
    Cartney
    2.61
    Activations Density 0.008%

    No Known Activations