© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 10746
    Prev
    Next
    INDEX
    Explanations

    predictive, smooth, controlled, use, padding

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

    The neuron responds strongly to low-frequency, standout content words—i.e., rare or unexpected tokens in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    createdBy
    0.63
    executions
    0.61
    timing
    0.60
    빚
    0.60
    monthly
    0.59
    inizio
    0.59
    Ago
    0.58
     совмести
    0.58
    쨰
    0.58
    diri
    0.57
    POSITIVE LOGITS
     Franken
    0.58
     Central
    0.57
     Hands
    0.55
     MOST
    0.55
     most
    0.54
     low
    0.54
     By
    0.54
     quieres
    0.53
     reverses
    0.53
     manca
    0.53
    Activations Density 0.000%

    No Known Activations