© 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. 9357
    Prev
    Next
    INDEX
    Explanations

    .

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

    The neuron responds strongly to uncommon or low‐frequency tokens (e.g. rare proper nouns, specific years, or unusual 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_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
     Craft
    0.77
     T
    0.72
     As
    0.69
    ية
    0.69
     Victim
    0.69
    ς
    0.69
    kich
    0.68
     Organ
    0.68
     Station
    0.68
     Pharmaceutical
    0.67
    POSITIVE LOGITS
    निय
    0.83
    ImageBeforeText
    0.80
    Otp
    0.75
    CBUUID
    0.74
    sendBuf
    0.73
    ApiCalls
    0.73
    prova
    0.73
    orderLine
    0.73
    BackendAuth
    0.73
    𝓾
    0.72
    Activations Density 0.001%

    No Known Activations