© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 108635
    Prev
    Next
    INDEX
    Explanations

    bit or bits

    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
     missione
    -0.72
     BUTTON
    -0.71
     musculoskeletal
    -0.70
    лык
    -0.70
    brador
    -0.69
    itra
    -0.69
    BadRequest
    -0.69
     بص
    -0.68
    Iraq
    -0.68
    ліст
    -0.67
    POSITIVE LOGITS
     bit
    4.31
     bits
    3.67
    bit
    3.56
    Bit
    3.19
     Bit
    3.05
    bits
    2.77
     Bits
    2.48
    BIT
    2.41
    Bits
    2.34
     BIT
    2.31
    Activations Density 0.078%

    No Known Activations