© 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. 12336
    Prev
    Next
    INDEX
    Explanations

    error messages

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

    The neuron fires on the main predicate of a sentence—especially core verbs (like “log,” “is,” “access,” “describes”) that introduce what something does or what it is.

    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
    atibus
    0.68
    ㅉ
    0.61
    வனாக
    0.59
    writeObject
    0.57
     informational
    0.56
    জনাব
    0.56
     संश्
    0.54
    ikle
    0.54
     digested
    0.54
     userInfo
    0.54
    POSITIVE LOGITS
    神
    0.61
     `
    0.61
    `,
    0.60
    「
    0.59
     `,
    0.57
    寺
    0.57
    Winter
    0.56
    Los
    0.55
    `
    0.54
    狩
    0.54
    Activations Density 0.001%

    No Known Activations