© 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. 78805
    Prev
    Next
    INDEX
    Explanations

    local favorites

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

    less than 10 years

    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
    λώ
    0.49
    本来
    0.46
    লিত
    0.46
    ৌম
    0.45
     comunica
    0.45
    ﮐ
    0.44
     podían
    0.43
    একদিন
    0.43
     giusto
    0.43
     Bakın
    0.43
    POSITIVE LOGITS
    cure
    0.50
     классов
    0.46
     रिकॉर्ड
    0.46
     Hawaiian
    0.44
     நப
    0.44
    人を
    0.44
    izzeria
    0.44
     российских
    0.43
     बड़े
    0.43
    s
    0.43
    Activations Density 0.000%

    No Known Activations