© 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. 194626
    Prev
    Next
    INDEX
    Explanations

    results, acquire, rush

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

    describing steps and evaluations

    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
     还
    0.52
    还
    0.52
    无
    0.44
     भरोसे
    0.44
     didn
    0.43
    last
    0.42
    未
    0.42
     MB
    0.41
    后
    0.41
     带
    0.40
    POSITIVE LOGITS
     gols
    0.54
     portray
    0.53
     tessel
    0.52
    שית
    0.52
     известный
    0.52
     portrays
    0.50
     enseignants
    0.50
     açısından
    0.49
    ‌های
    0.49
     cadast
    0.49
    Activations Density 0.001%

    No Known Activations