© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 9885
    Prev
    Next
    INDEX
    Explanations

    experience commitment

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

    The neuron is keyed to formal informational and disclaimer–style terms (e.g. “references,” “descriptions,” “additionally,” “provided,” “combining,” “research”) typical of legal or technical documentation.

    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
     оператив
    0.59
    lekt
    0.57
     핵심
    0.56
     worldview
    0.55
     hindsight
    0.54
     interpersonal
    0.54
     introspection
    0.53
    텍
    0.53
     ذہنی
    0.53
    BufOffset
    0.52
    POSITIVE LOGITS
     dealings
    0.74
     dealing
    0.62
    dealing
    0.61
    扱
    0.61
     về
    0.59
    Dealing
    0.57
    关于
    0.57
     Aspects
    0.57
     aandacht
    0.57
     inroads
    0.57
    Activations Density 0.775%

    No Known Activations