© 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. 81513
    Prev
    Next
    INDEX
    Explanations

    lists page

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

    understanding instructions

    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
    ING
    0.54
     dáv
    0.46
    싶
    0.44
     বিচারের
    0.44
    داف
    0.43
     closets
    0.42
     GeV
    0.42
    ức
    0.42
    候
    0.42
    čit
    0.41
    POSITIVE LOGITS
     analogue
    0.50
     அவரு
    0.48
    Message
    0.48
     substance
    0.47
    Media
    0.46
    ですよ
    0.46
    л
    0.46
     l
    0.46
    です
    0.46
    だよ
    0.45
    Activations Density 0.000%

    No Known Activations