© 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. 7564
    Prev
    Next
    INDEX
    Explanations

    lucky, generous, fortunate

    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
    life
    0.64
     previo
    0.64
     inci
    0.63
    SPE
    0.60
     sker
    0.59
    ées
    0.59
    ']),
    0.59
     espaces
    0.58
     Complaints
    0.58
     CHECK
    0.58
    POSITIVE LOGITS
    ことに
    0.77
     wording
    0.75
     omitting
    0.73
    과
    0.72
    이나
    0.71
     ट्रिक
    0.71
     lenient
    0.71
    もあり
    0.70
     사용하여
    0.70
     بشأن
    0.70
    Activations Density 0.003%

    No Known Activations