© 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. 20283
    Prev
    Next
    INDEX
    Explanations

    important than, review by, most especially

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

    book summaries and educational content

    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
    лено
    0.52
    мене
    0.46
    ро
    0.45
    খ
    0.45
     Oaks
    0.45
    鵑
    0.44
    ક્ષ
    0.44
    يين
    0.44
    ה
    0.43
     giản
    0.42
    POSITIVE LOGITS
    seye
    0.48
    :“
    0.48
     claims
    0.47
     indicates
    0.47
     eftersom
    0.47
     தயார
    0.47
    pier
    0.46
    EB
    0.46
     ತಯಾರ
    0.46
     Hwang
    0.46
    Activations Density 0.000%

    No Known Activations