© 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. 3898
    Prev
    Next
    INDEX
    Explanations

    friend or prepared

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

    The neuron selectively responds to infrequent or unusual words (i.e. rare vocabulary or jargon).

    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
    聩
    0.70
    萧
    0.69
    你可以
    0.68
     ingrédients
    0.66
     cherished
    0.65
     composants
    0.65
    тті
    0.61
    竣
    0.61
    slaught
    0.61
    ＝＝
    0.61
    POSITIVE LOGITS
    in
    1.04
     kaum
    0.94
     meist
    0.87
     PHYS
    0.86
    ist
    0.86
    og
    0.86
     Fischer
    0.84
    lord
    0.83
    IN
    0.82
    anderen
    0.82
    Activations Density 0.000%

    No Known Activations