© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 1584
    Prev
    Next
    INDEX
    Explanations

    style | based | driven

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-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
    -
    2.06
    -<
    1.47
    の中で
    1.43
    -*
    1.35
    (
    1.32
     proceeds
    1.31
    最大の
    1.23
    annya
    1.20
    (~
    1.20
     curvatures
    1.20
    POSITIVE LOGITS
    based
    2.86
    ع
    2.73
    type
    2.70
    friendly
    2.67
    под
    2.53
    мене
    2.52
    مح
    2.51
    اك
    2.51
    мар
    2.50
    листи
    2.49
    Activations Density 0.561%

    No Known Activations