© 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. 24-GEMMASCOPE-2-RES-16K
    7. 2445
    Prev
    Next
    INDEX
    Explanations

    This neuron strongly activates on alphanumeric tokens or sequences (e.g. citation/journal abbreviations, chess‐move codes, mixed letter‐digit IDs), i.e. technical identifiers.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    formal information

    np_max-act · claude-4-5-sonnetTriggered by @jrosseruk
    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
     reputed
    0.72
     Regards
    0.71
     MIF
    0.70
     MACHIN
    0.67
     Croft
    0.67
     वाणी
    0.66
    清楚
    0.65
    큰
    0.65
    日至
    0.65
     WORKING
    0.65
    POSITIVE LOGITS
     ու
    0.91
    ou
    0.86
     เรื่อง
    0.80
    m
    0.79
    trom
    0.76
    ov
    0.75
    比如
    0.75
    empl
    0.73
    tilde
    0.73
    cil
    0.73
    Activations Density 0.000%

    No Known Activations