© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 24-GEMMASCOPE-2-RES-262K
    7. 8974
    Prev
    Next
    INDEX
    Explanations

    who, where, clicking, get, requests, change

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_24_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    :
    0.80
    ,
    0.68
     -
    0.59
     :
    0.54
     ,
    0.54
    ®,
    0.52
    ®
    0.51
    ;
    0.50
    ":
    0.50
    0.49
    POSITIVE LOGITS
     pagamento
    0.66
     altercation
    0.63
     notificación
    0.63
     notificações
    0.63
     paiement
    0.62
     jemand
    0.62
     chiesto
    0.62
     screenshots
    0.61
     miał
    0.59
     décès
    0.59
    Activations Density 0.012%

    No Known Activations