© 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. 22-GEMMASCOPE-RES-131K
    7. 39057
    Prev
    Next
    INDEX
    Explanations

    specific tokens like ff, Result, John, double, js

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

    The neuron is detecting standalone numeric tokens (numbers and numeric values) in the text.

    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
    Ẻ
    -0.90
    фия
    -0.89
     dotyczą
    -0.88
    ")));
    -0.85
    >%
    -0.84
    LEAN
    -0.84
     :"
    -0.82
    .}\
    -0.82
     dergleichen
    -0.82
    "$
    -0.81
    POSITIVE LOGITS
    ِّ
    0.88
     with
    0.86
     davvero
    0.86
     their
    0.85
     COLLE
    0.82
     bancaria
    0.79
     dauern
    0.77
     نداره
    0.76
     lunghi
    0.76
     seleccionado
    0.75
    Activations Density 0.112%

    No Known Activations