© 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. 12296
    Prev
    Next
    INDEX
    Explanations

    JSON code snippets

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

    The neuron fires on numeric tokens representing floating-point values (decimal numbers).

    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
    ↵↵↵
    0.66
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.63
     Success
    0.63
    ↵↵↵↵
    0.62
    ↵↵↵↵↵↵↵
    0.62
    Success
    0.61
    слава
    0.61
    ↵↵↵↵↵
    0.60
     }}{\
    0.59
    ↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.58
    POSITIVE LOGITS
     Hart
    0.66
     Q
    0.62
     magnitude
    0.58
     inext
    0.57
     CFO
    0.56
    magnitude
    0.55
     stear
    0.55
    vre
    0.55
     absorbance
    0.55
     rooft
    0.54
    Activations Density 0.168%

    No Known Activations