© 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. 187440
    Prev
    Next
    INDEX
    Explanations

    legal, financial, and technical documents

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

    downloading files or updates

    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
     froide
    0.50
     مخالف
    0.46
     Rodr
    0.45
    ុ
    0.45
     revol
    0.44
     peint
    0.43
     bog
    0.43
     வாய
    0.43
    付き
    0.43
    あまり
    0.43
    POSITIVE LOGITS
    ⑤
    0.47
    ंठ
    0.45
    ADT
    0.43
    락
    0.43
    ៤
    0.43
    搶
    0.43
    5
    0.42
    IPO
    0.42
    찮
    0.42
    ⑥
    0.42
    Activations Density 0.000%

    No Known Activations