© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 6466
    Prev
    Next
    INDEX
    Explanations

    essential, pseudo, lens, electoral

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    쇤
    0.45
    룀
    0.44
    工作中
    0.44
     powerAll
    0.44
    ’).
    0.43
    вими
    0.43
    蒿
    0.41
    蛻
    0.41
    [multimodal]
    0.41
    푐
    0.41
    POSITIVE LOGITS
    uto
    0.48
    ra
    0.48
    ato
    0.45
    ua
    0.45
    ju
    0.45
    uju
    0.44
     Wu
    0.42
    ami
    0.41
     juj
    0.41
    je
    0.41
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.