© 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. 63388
    Prev
    Next
    INDEX
    Explanations

    present study or criminal appeals

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

    This neuron responds to tokens that are numeric or numeric-containing identifiers (e.g. version numbers, character encodings, dimensions, or hyphenated digit strings).

    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
    活
    -0.67
     Cic
    -0.65
     univers
    -0.65
     asistente
    -0.64
     clamped
    -0.63
     Thayer
    -0.63
    ralph
    -0.62
     réal
    -0.62
     Shy
    -0.61
    大了
    -0.60
    POSITIVE LOGITS
    access
    0.78
    arra
    0.77
    jiro
    0.75
     obyvateľov
    0.69
    ACGIH
    0.68
    APPLAUSE
    0.67
     cámara
    0.67
     Tiberius
    0.67
     годах
    0.66
    agin
    0.65
    Activations Density 0.071%

    No Known Activations