© 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. 13580
    Prev
    Next
    INDEX
    Explanations

    this less

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

    shock, disrupt, downloads, cards, technology

    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
    фы
    0.52
    riet
    0.49
     过
    0.48
    דת
    0.46
    licted
    0.46
     写
    0.46
    ㄾ
    0.45
    roa
    0.45
    FindFileData
    0.45
     书
    0.44
    POSITIVE LOGITS
    िक
    0.56
     credibility
    0.54
     Cerc
    0.52
     plaques
    0.50
     collectives
    0.49
     dictionaries
    0.49
     identification
    0.47
     schemas
    0.47
     spheres
    0.46
     Inform
    0.46
    Activations Density 0.000%

    No Known Activations