© 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. 70872
    Prev
    Next
    INDEX
    Explanations

    phrases indicating availability or responsibility

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

    introduces explanation or description

    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
    ﺎ
    0.53
    性を
    0.48
    घटना
    0.48
    ﻐ
    0.46
    गृ
    0.46
    गज
    0.44
    вающие
    0.44
     नव
    0.44
    osse
    0.44
    性は
    0.44
    POSITIVE LOGITS
     짜
    0.51
     DIAG
    0.47
    p
    0.47
     sprites
    0.46
     televisie
    0.45
    చారం
    0.44
     nitrification
    0.44
    Ć
    0.44
     diplomas
    0.43
     psia
    0.43
    Activations Density 0.001%

    No Known Activations