© 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. 160492
    Prev
    Next
    INDEX
    Explanations

    analysis, evaluation, or state

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

    spoilage, day, only, persist, instantly, Pennsylvania

    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
    ності
    0.50
     রোধ
    0.50
     Distinction
    0.48
    স্থ
    0.47
     অনুস
    0.46
     podmín
    0.46
    ۥ
    0.46
     Conditions
    0.45
     Away
    0.45
     circumstance
    0.44
    POSITIVE LOGITS
     voxel
    0.49
     analisa
    0.48
     분석
    0.47
     analyser
    0.47
     análise
    0.46
     onset
    0.45
    嘉
    0.45
    തേ
    0.44
     anál
    0.44
    動畫
    0.42
    Activations Density 0.001%

    No Known Activations