© 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. 22-GEMMASCOPE-RES-131K
    7. 15484
    Prev
    Next
    INDEX
    Explanations

    pain relief

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

    file extensions and identifiers in programming code or technical documentation.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron fires on numeric tokens (digits and multi‐digit numbers), e.g. version numbers, macro constants, line numbers, etc.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     eenige
    -0.98
     juft
    -0.98
    mètres
    -0.97
    !#
    -0.96
    loren
    -0.96
     PROGRAMME
    -0.95
    teve
    -0.94
    ではありません
    -0.94
    cryption
    -0.94
    BitConverter
    -0.93
    POSITIVE LOGITS
    abetes
    1.10
    Reak
    1.02
     asesoramiento
    1.00
     surtido
    0.99
     nutrición
    0.98
     теперь
    0.97
     necessità
    0.96
    많
    0.96
     liderazgo
    0.96
     hogares
    0.95
    Activations Density 0.001%

    No Known Activations