© 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. 8929
    Prev
    Next
    INDEX
    Explanations

    thawing this way

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

    This neuron lights up on unusually rare or low‐frequency tokens (i.e. uncommon words).

    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
    Capricorn
    0.74
    Seller
    0.72
    ('/');
    0.71
    Towards
    0.68
    Uncle
    0.68
    PayPal
    0.67
    she
    0.66
    Charges
    0.66
    ToSend
    0.65
    sche
    0.65
    POSITIVE LOGITS
    ла
    0.90
    ază
    0.89
     leukocytes
    0.89
     economists
    0.87
     sanctuaries
    0.87
     cleaners
    0.86
    ت
    0.86
     pathologists
    0.84
     exceptions
    0.83
     vegetarians
    0.83
    Activations Density 0.000%

    No Known Activations