© 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. 31-GEMMASCOPE-2-RES-16K
    7. 13552
    Prev
    Next
    INDEX
    Explanations

    ice cream, ice cores

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

    This neuron detects references to ice, glaciers, frost, or other freezing/frozen elements and related cold-environment terms.

    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
     விச
    0.59
    ♎
    0.57
    ặng
    0.53
     நட்ப
    0.53
    ogaster
    0.53
     Malaga
    0.53
     хро
    0.52
     Rainfall
    0.52
    缙
    0.52
     ভিয়েতনাম
    0.52
    POSITIVE LOGITS
     ice
    2.83
    冰
    2.69
     Ice
    2.61
    氷
    2.61
    Ice
    2.55
     frozen
    2.48
     hielo
    2.36
     Frozen
    2.30
    Frozen
    2.30
     freezing
    2.19
    Activations Density 0.355%

    No Known Activations