© 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. 85598
    Prev
    Next
    INDEX
    Explanations

    Debtor

    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
     collaborate
    -2.94
     všech
    -2.81
     convince
    -2.81
     —
    -2.80
     eigenen
    -2.78
     neuen
    -2.77
     idyllic
    -2.75
     dvou
    -2.73
     dreamy
    -2.73
     terrifying
    -2.72
    POSITIVE LOGITS
     parachoque
    3.13
    >
    2.95
    宬
    2.92
     leone
    2.89
    🌻
    2.88
     estadounid
    2.88
     westfalen
    2.84
    毉
    2.84
     セックス
    2.83
     muft
    2.83
    Activations Density 0.007%

    No Known Activations