© 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. 88619
    Prev
    Next
    INDEX
    Explanations

    website and page links

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

    resolution China hides uses too

    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
    Ɩ
    0.46
    aaa
    0.46
    aaaa
    0.44
    excitation
    0.42
    माला
    0.42
     حتی
    0.42
     অভ
    0.41
     sprouting
    0.41
     strokes
    0.40
    >)</
    0.40
    POSITIVE LOGITS
     компью
    0.45
    elesaikan
    0.43
     фер
    0.42
     особи
    0.42
    시스템
    0.41
     impatience
    0.40
    OLS
    0.40
     Respondent
    0.40
     проб
    0.40
    Respondent
    0.39
    Activations Density 0.002%

    No Known Activations