© 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. 69684
    Prev
    Next
    INDEX
    Explanations

    model metrics

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

    constructive feedback and recognition

    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
     k
    0.48
     oh
    0.48
    犧
    0.46
     kor
    0.46
     kob
    0.45
     rhet
    0.44
     kal
    0.44
     nights
    0.44
     kontroll
    0.44
     illusions
    0.43
    POSITIVE LOGITS
    propylene
    0.46
    韆
    0.44
    .[[
    0.44
    зию
    0.43
     substantiated
    0.43
    受理
    0.42
     проду
    0.42
    ছনে
    0.42
    rawValue
    0.41
    айл
    0.41
    Activations Density 0.001%

    No Known Activations