© 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. 34-GEMMASCOPE-RES-131K
    7. 117690
    Prev
    Next
    INDEX
    Explanations

    DW Magz theme

    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
    bringer
    -0.85
    肚
    -0.81
     maak
    -0.81
    бовь
    -0.79
    лера
    -0.79
    cerita
    -0.78
    nextProps
    -0.78
    PushMatrix
    -0.77
    imarães
    -0.77
    estrian
    -0.75
    POSITIVE LOGITS
    时空
    0.88
    Enfer
    0.79
    >
    0.79
    いら
    0.77
     $>
    0.76
     >
    0.76
     >
    0.75
    Raúl
    0.74
     erstre
    0.73
    Karin
    0.73
    Activations Density 0.021%

    No Known Activations