© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 119811
    Prev
    Next
    INDEX
    Explanations

    all finite

    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
    columnwidth
    -1.71
     Septembre
    -1.60
     "
    -1.58
    }}{\
    -1.57
     ",
    -1.57
    ९
    -1.56
    ícia
    -1.55
    ॆ
    -1.52
    ।
    -1.52
    providedIn
    -1.51
    POSITIVE LOGITS
     with
    2.11
     Perhaps
    1.75
    Pengertian
    1.72
    Perhaps
    1.70
    Ար
    1.70
    Surprisingly
    1.60
     Sometimes
    1.59
     vaksin
    1.55
    While
    1.55
    There
    1.55
    Activations Density 0.156%

    No Known Activations