© 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. 141596
    Prev
    Next
    INDEX
    Explanations

    BBQ sauce, electric wires, room+

    np_acts-logits-general · gemini-2.5-flash-lite

    complex nouns and following words

    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
    ি
    0.46
    镛
    0.46
    髡
    0.44
     pály
    0.44
    杜
    0.43
    ாட
    0.42
    क्षम
    0.41
    ι
    0.41
     সাহ
    0.41
    िक
    0.40
    POSITIVE LOGITS
     punishable
    0.52
     buoyancy
    0.52
     oligarch
    0.52
     bullied
    0.50
    oloog
    0.50
     無料
    0.50
    lasz
    0.50
     interplanetary
    0.49
     bullying
    0.48
     interlayer
    0.48
    Activations Density 0.000%

    No Known Activations