© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 609
    Prev
    Next
    INDEX
    Explanations

    product model identifiers

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

    This neuron detects technical model numbers and specification tokens (alphanumeric sequences and numeric measurements) 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_24_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
    addEnemy
    0.47
    GLIGENCE
    0.44
    infoHeader
    0.42
    bgColor
    0.42
    읊
    0.41
    regexp
    0.40
    encerramento
    0.40
    ulnerable
    0.40
    ieties
    0.39
     बीसीजी
    0.39
    POSITIVE LOGITS
     X
    0.53
     series
    0.52
     Deluxe
    0.52
    シリーズ
    0.51
    ™
    0.51
     M
    0.49
     Series
    0.49
     with
    0.49
     รุ่น
    0.49
     terbaru
    0.49
    Activations Density 0.306%

    No Known Activations