© 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. 34-GEMMASCOPE-RES-131K
    7. 99760
    Prev
    Next
    INDEX
    Explanations

    followed by down

    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_34/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
    VisualStudio
    -0.77
     Darwin
    -0.76
    oggi
    -0.73
    Kno
    -0.73
    szer
    -0.73
     Lott
    -0.72
    bertas
    -0.71
    ciamo
    -0.71
    gment
    -0.71
    IBOutlet
    -0.69
    POSITIVE LOGITS
     down
    5.50
    down
    2.95
    Down
    2.66
     DOWN
    2.42
     Down
    2.31
     вниз
    2.09
    DOWN
    2.08
     up
    1.95
    ダウン
    1.63
    ลง
    1.58
    Activations Density 0.070%

    No Known Activations