© 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. 239904
    Prev
    Next
    INDEX
    Explanations

    SEO optimization

    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
    𝗍
    0.48
     принимает
    0.47
     ஒளி
    0.45
    Τ
    0.43
     принима
    0.43
    瞪
    0.42
    推送
    0.41
     doença
    0.41
    ∑
    0.40
    și
    0.40
    POSITIVE LOGITS
     fres
    0.47
    jir
    0.46
    usel
    0.45
    baz
    0.44
    ကား
    0.44
    jerne
    0.44
     or
    0.43
     splurge
    0.43
     fahren
    0.43
     চালাতে
    0.43
    Activations Density 0.001%

    No Known Activations