© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 3734
    Prev
    Next
    INDEX
    Explanations

    options, filings, or other structured information

    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_16k_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
    笵
    1.14
    ный
    1.03
    يش
    1.03
    ного
    0.99
    的行为
    0.99
    dır
    0.98
    و
    0.98
    plätze
    0.97
    䅧
    0.97
    OfWeek
    0.96
    POSITIVE LOGITS
    NA
    1.08
    2
    0.99
    Match
    0.95
    RI
    0.94
    1
    0.92
    3
    0.92
     a
    0.86
    art
    0.86
    SA
    0.86
     Match
    0.86
    Activations Density 0.003%

    No Known Activations