© 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. 95360
    Prev
    Next
    INDEX
    Explanations

    added code lines

    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
     Север
    0.48
     അദ്ദേഹ
    0.46
     සී
    0.46
     Пер
    0.45
     北
    0.44
     թվական
    0.44
     Institution
    0.43
     Netherlands
    0.43
     整
    0.43
    rapid
    0.42
    POSITIVE LOGITS
    로나
    0.42
     toilets
    0.41
    ASON
    0.40
     cures
    0.40
    ंधन
    0.40
     differenti
    0.40
     Browne
    0.40
    JO
    0.39
    फना
    0.39
    มาะ
    0.39
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.