© 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. 209339
    Prev
    Next
    INDEX
    Explanations

    bar soap or medical improvement

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

    program deployment and connection

    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
    на
    0.52
     sanitaria
    0.51
     woodland
    0.49
     considerazione
    0.48
     poultry
    0.47
    oders
    0.47
    Ꮽ
    0.46
     Stell
    0.46
     especializada
    0.46
    VERSE
    0.46
    POSITIVE LOGITS
    æt
    0.48
     مفید
    0.48
     আচরণ
    0.47
     أعلام
    0.46
    etime
    0.44
    憊
    0.43
     ডি
    0.43
    মতো
    0.42
    attering
    0.42
    otype
    0.42
    Activations Density 0.000%

    No Known Activations