© 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. 174029
    Prev
    Next
    INDEX
    Explanations

    emphasis and quotes

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

    translated and emphasized text

    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
     temporada
    0.44
    鬧
    0.41
    jších
    0.40
    데이트
    0.40
     temporadas
    0.38
    bagi
    0.37
    ùa
    0.36
    𝐴
    0.36
     Hinter
    0.35
    datepicker
    0.35
    POSITIVE LOGITS
    emphasis
    0.84
     emphasis
    0.80
     paraphr
    0.76
     Emphasis
    0.76
    Emphasis
    0.75
     énfasis
    0.67
     verbatim
    0.66
     paraphrase
    0.65
     emph
    0.63
    強調
    0.61
    Activations Density 0.040%

    No Known Activations