© 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. 72457
    Prev
    Next
    INDEX
    Explanations

    results, scores, votes

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

    depending on, requires strong, by votes

    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
     destinés
    0.49
     modulate
    0.46
     destinée
    0.45
    ૂર
    0.43
    φ
    0.41
    θη
    0.40
     শত্র
    0.40
     rhet
    0.40
     Rouen
    0.39
     collectively
    0.39
    POSITIVE LOGITS
     등이
    0.47
     결과
    0.46
    成绩
    0.46
     результа
    0.44
     عمل
    0.44
     नतीजा
    0.44
    虧
    0.44
     scorecard
    0.44
     результата
    0.43
     انھوں
    0.43
    Activations Density 0.001%

    No Known Activations