© 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. 34-GEMMASCOPE-RES-131K
    7. 90654
    Prev
    Next
    INDEX
    Explanations

    at least

    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
     despite
    -0.74
    ="#"
    -0.73
    俎
    -0.73
     ISLANDS
    -0.72
    зен
    -0.72
     on
    -0.71
    嗣
    -0.71
     or
    -0.69
     of
    -0.68
    ramientas
    -0.68
    POSITIVE LOGITS
     minimum
    3.39
    minimum
    2.92
     mínimo
    2.66
     MINIMUM
    2.23
    Minimum
    2.20
    MINIMUM
    2.11
     Minimum
    2.06
     least
    2.02
     mínima
    1.98
     حداقل
    1.91
    Activations Density 0.017%

    No Known Activations