© 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. 8210
    Prev
    Next
    INDEX
    Explanations

    javascript code or names

    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
    м
    3.80
    ле
    2.81
    л
    2.36
    на
    2.27
    م
    2.23
    ি
    2.16
    ン
    2.14
    а
    2.11
    ी
    2.08
    и
    2.03
    POSITIVE LOGITS
    ς
    2.86
    s
    2.48
    sion
    2.11
    um
    2.06
    sylvania
    2.06
    sType
    1.97
    멩
    1.95
    slope
    1.95
    他
    1.93
    snippets
    1.92
    Activations Density 0.212%

    No Known Activations