© 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. 11923
    Prev
    Next
    INDEX
    Explanations

    without warranty

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

    The neuron detects “as is” warranty‐disclaimer language commonly found in legal boilerplate.

    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
     النت
    0.65
     仕事
    0.59
    เกิดขึ้น
    0.57
     Mi
    0.57
     Youtube
    0.56
     Eh
    0.55
     Cam
    0.55
    -])
    0.54
     सहानुभूति
    0.54
     Camar
    0.54
    POSITIVE LOGITS
    <unused26>
    0.66
    elas
    0.60
    ກັບ
    0.59
    sans
    0.57
    ΑΣ
    0.55
    dus
    0.55
     což
    0.54
    styling
    0.54
    يرا
    0.53
    excluding
    0.53
    Activations Density 0.003%

    No Known Activations