© 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. 183371
    Prev
    Next
    INDEX
    Explanations

    interviewed, step, Thank you, topics and, fine and

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

    program, allocation, profile, standards, graft, assessment, management, generation

    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
    誣
    0.41
     annum
    0.41
     belang
    0.41
     ataupun
    0.40
    cyclo
    0.39
     Incub
    0.39
     r
    0.38
    たた
    0.38
     Kreat
    0.38
    BackgroundHelper
    0.38
    POSITIVE LOGITS
    "]]
    0.57
     ناو
    0.57
    ólito
    0.51
    '...
    0.50
    :",
    0.50
     আত্মার
    0.49
    '}}
    0.49
    ियाँ
    0.49
     invertir
    0.48
    ofy
    0.48
    Activations Density 0.000%

    No Known Activations