© 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. 76833
    Prev
    Next
    INDEX
    Explanations

    sup. . count groupfirefighters service women title

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

    The neuron activates on numeric tokens or digit sequences (e.g. version numbers, counts, indexes).

    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
     schon
    -0.79
    lep
    -0.78
    siede
    -0.77
    argout
    -0.76
     už
    -0.75
     theor
    -0.75
     should
    -0.75
    cours
    -0.73
    Lemma
    -0.73
    iffel
    -0.71
    POSITIVE LOGITS
     tentativo
    0.80
     gesamten
    0.79
    Abrir
    0.78
     (_)
    0.78
     なし
    0.77
     emper
    0.76
     abate
    0.76
     Mue
    0.76
    raszam
    0.76
    Título
    0.76
    Activations Density 0.000%

    No Known Activations