© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 78285
    Prev
    Next
    INDEX
    Explanations

    sha hashes and copyright notices

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron fires on alphanumeric tokens that include digits—e.g. version numbers, charset/encoding labels, hash-algorithm names, and similar technical identifiers.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     daudz
    -0.86
    trang
    -0.81
    estatus
    -0.79
    ルター
    -0.77
    ⿻
    -0.77
     vairāk
    -0.76
    じて
    -0.76
    十五
    -0.75
     Verfahrens
    -0.73
    tové
    -0.73
    POSITIVE LOGITS
     razor
    0.98
    ஏ
    0.85
     complementary
    0.81
     magnifique
    0.78
     raz
    0.78
     moderne
    0.77
     conserver
    0.77
     impon
    0.77
    ARSE
    0.76
     vokal
    0.76
    Activations Density 0.003%

    No Known Activations