© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 1924
    Prev
    Next
    INDEX
    Explanations

    don't reveal everything

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_65k_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
    /
    0.44
    -
    0.38
     snippets
    0.38
     অর্থাৎ
    0.37
    比如
    0.35
    Keep
    0.35
    Apps
    0.34
    From
    0.34
     counterparts
    0.34
    Give
    0.34
    POSITIVE LOGITS
     wyłącznie
    0.50
    <unused636>
    0.38
    粎
    0.38
     racional
    0.36
    থানি
    0.36
     ജില്ലാ
    0.35
    exactly
    0.35
    确实
    0.35
    ración
    0.34
    political
    0.33
    Activations Density 0.685%

    No Known Activations