© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 150053
    Prev
    Next
    INDEX
    Explanations

    lists with punctuation or conjunctions

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

    Edge Dislocation

    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
    Negative Logits
     backstory
    0.49
     culminating
    0.46
    ვის
    0.46
     deposits
    0.45
     🙌
    0.45
     setup
    0.44
     accum
    0.44
     deposit
    0.44
     সবচে
    0.44
     존
    0.44
    POSITIVE LOGITS
     reforma
    0.48
    PATCH
    0.47
    CH
    0.46
    AX
    0.46
    רום
    0.46
    FEN
    0.45
    假
    0.45
    arı
    0.45
    ACT
    0.44
    ГА
    0.44
    Activations Density 0.005%

    No Known Activations