© 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. 181766
    Prev
    Next
    INDEX
    Explanations

    created in God's nature

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

    colloidal silver, company, investing, sores, patches, potential, started talking, highest volume

    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
    o
    0.55
     दबाव
    0.46
     আঘাতে
    0.46
    stid
    0.45
    নং
    0.45
    oł
    0.45
    en
    0.45
    masına
    0.45
    enangan
    0.44
    FBSDKError
    0.44
    POSITIVE LOGITS
    介
    0.45
     Mishra
    0.44
    лли
    0.43
     polytope
    0.43
     lijn
    0.42
    usting
    0.42
    inture
    0.41
     öff
    0.41
     Ji
    0.41
    ومة
    0.41
    Activations Density 0.000%

    No Known Activations