© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 53757
    Prev
    Next
    INDEX
    Explanations

    io and 要

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ಙ
    0.43
    équipement
    0.42
    bytecode
    0.41
    classification
    0.41
    whitelist
    0.41
     Після
    0.41
     Commencement
    0.41
    ಐ
    0.40
    underbrace
    0.40
     Statute
    0.40
    POSITIVE LOGITS
     harms
    0.50
     costs
    0.49
    要
    0.47
     vere
    0.47
     make
    0.45
     harm
    0.45
     pleinement
    0.44
    错过
    0.44
     de
    0.42
     interess
    0.42
    Activations Density 0.015%

    No Known Activations