© 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. 149877
    Prev
    Next
    INDEX
    Explanations

    US American Saturday download

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

    significant launch

    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
    월
    0.55
    PathOf
    0.51
     อำ
    0.50
     isomorphism
    0.48
    쓰
    0.48
    เอก
    0.48
     transferência
    0.47
     уровне
    0.47
     euer
    0.47
     efek
    0.46
    POSITIVE LOGITS
     Remaining
    0.48
     restante
    0.46
     remaining
    0.46
     Reject
    0.45
    ’
    0.42
     neutralizing
    0.41
    hline
    0.40
     Combs
    0.40
    屒
    0.40
     rejection
    0.40
    Activations Density 0.000%

    No Known Activations