© 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. 22-GEMMASCOPE-RES-131K
    7. 98387
    Prev
    Next
    INDEX
    Explanations

    first followed by ordinal indicators

    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_22/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
    <bos>
    -1.25
    もしれない
    -1.16
    เขา
    -1.06
     idea
    -1.02
     PUSTAKA
    -0.98
     jednego
    -0.97
    Chairs
    -0.93
     bisherigen
    -0.93
    참고
    -0.92
    ıc
    -0.92
    POSITIVE LOGITS
    Bahkan
    1.19
    providedIn
    1.15
    祤
    1.07
    \}
    1.06
    1.05
    و
    1.05
    ooo
    1.03
    Kaip
    1.01
    uertos
    1.01
    izes
    1.01
    Activations Density 0.035%

    No Known Activations