© 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. 10-GEMMASCOPE-RES-131K
    7. 39681
    Prev
    Next
    INDEX
    Explanations

    identifiers, and list items

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

    The neuron strongly activates on isolated numeric tokens and related punctuation (digits, parentheses, version‐style markers).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    no
    -1.61
    1
    -1.54
    We
    -1.53
    9
    -1.53
    e
    -1.47
    er
    -1.45
    In
    -1.45
    A
    -1.41
    ve
    -1.40
    g
    -1.40
    POSITIVE LOGITS
     清新
    1.56
     *}$
    1.49
    .}(
    1.48
    lerinden
    1.45
    ResumeLayout
    1.44
    szt
    1.43
     {
    1.41
    🍻
    1.41
    >
    1.41
    .$.
    1.41
    Activations Density 0.000%

    No Known Activations