© 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. 123839
    Prev
    Next
    INDEX
    Explanations

    names, places, and descriptions

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

    understanding tasks and roleplaying

    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
    \%),
    0.49
     explicitly
    0.47
     проде
    0.47
     cytokines
    0.46
     खुलासा
    0.46
     revealed
    0.46
     choline
    0.45
     totalSupply
    0.45
    তুর
    0.45
    もある
    0.45
    POSITIVE LOGITS
    ników
    0.46
     اکس
    0.43
    endering
    0.43
    venido
    0.42
    م
    0.42
    iet
    0.41
     ध
    0.41
     언
    0.41
    ed
    0.41
    PUSH
    0.41
    Activations Density 0.000%

    No Known Activations