© 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. 24-GEMMASCOPE-2-RES-16K
    7. 9770
    Prev
    Next
    INDEX
    Explanations

    text-align: center

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

    This neuron spikes on legal‐boilerplate scope/limitation phrases—e.g. “to the extent permitted by law,” “in connection with,” “arising out of,” etc.

    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
    Lk
    0.87
     тыс
    0.80
    prisoners
    0.71
     pierws
    0.71
    η
    0.70
    คว
    0.69
    boston
    0.68
    +}$,
    0.68
    akov
    0.68
     apie
    0.68
    POSITIVE LOGITS
     ゙
    0.84
     interfacing
    0.81
     নিজেও
    0.79
     कोणत्याही
    0.77
     underwriting
    0.75
     द्वी
    0.73
     حي
    0.73
     fatto
    0.71
     усі
    0.70
    沺
    0.70
    Activations Density 0.001%

    No Known Activations