© 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. 108900
    Prev
    Next
    INDEX
    Explanations

    numeric literal definitions

    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
     maska
    -0.82
    wys
    -0.82
    افز
    -0.81
    女儿
    -0.79
    coca
    -0.77
     majorité
    -0.76
     Sting
    -0.74
    বার
    -0.74
     BUCK
    -0.73
    Sting
    -0.73
    POSITIVE LOGITS
    hh
    0.88
     oct
    0.83
     BigDecimal
    0.79
    numeric
    0.79
    scientific
    0.77
    ษ
    0.76
     scientific
    0.75
    mittance
    0.75
    BigInteger
    0.74
    ごちそうさまでした
    0.73
    Activations Density 0.012%

    No Known Activations