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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 31986
    Prev
    Next
    INDEX
    Explanations

    diagnoses and descriptions

    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_12_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
     ribonucle
    0.91
    鷄
    0.87
     nugget
    0.86
     microcos
    0.85
    ("-"*
    0.85
     aplicativo
    0.84
     nascimento
    0.84
     interação
    0.83
     lijst
    0.82
    すること
    0.82
    POSITIVE LOGITS
    le
    0.89
    able
    0.88
    er
    0.84
    u
    0.79
    la
    0.79
    pt
    0.77
    ga
    0.75
    ㎞
    0.75
    ✉
    0.73
    cares
    0.70
    Activations Density 0.000%

    No Known Activations