© 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. 2992
    Prev
    Next
    INDEX
    Explanations

    soft memory earmuffs

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

    The neuron flags segments that enumerate product specifications or detailed feature lists (e.g. dimensions, materials, ratings, and included items).

    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
     tzw
    0.78
     ૧
    0.70
    Laura
    0.67
    III
    0.64
    PROFILE
    0.64
     Lietuvos
    0.64
    Arizona
    0.63
     decked
    0.63
     III
    0.62
    Thursday
    0.61
    POSITIVE LOGITS
     ，
    0.95
     adsorption
    0.80
     exquis
    0.79
     handicrafts
    0.78
     Undoubtedly
    0.75
     ：
    0.75
    ，
    0.73
     netizens
    0.73
    丨
    0.72
     、
    0.71
    Activations Density 0.254%

    No Known Activations