© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 11876
    Prev
    Next
    INDEX
    Explanations

    medium effort

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

    The neuron is triggered by unusually rare or unexpected tokens (i.e. low‐frequency words) in the text.

    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
     consecutivos
    0.88
     municípios
    0.84
     सटीक
    0.84
     kilómetros
    0.83
     mensagens
    0.82
    朋
    0.81
     necesarias
    0.81
     relevantes
    0.80
     temporadas
    0.80
     universidades
    0.80
    POSITIVE LOGITS
    Eff
    0.86
    )
    0.77
    Illustration
    0.76
     একট
    0.74
    Aston
    0.73
    First
    0.72
    Bombay
    0.71
    Gur
    0.71
    Earlier
    0.71
    ❯
    0.71
    Activations Density 0.000%

    No Known Activations