© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 8998
    Prev
    Next
    INDEX
    Explanations

    current state, status, or approach

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ও
    0.63
     electrón
    0.53
    י
    0.53
    原理
    0.52
    変換
    0.52
    も
    0.50
     largas
    0.49
    后
    0.49
    以后
    0.49
    도
    0.49
    POSITIVE LOGITS
     현재
    0.68
     huidige
    0.68
    on
    0.64
    目前的
    0.64
     फिलहाल
    0.60
    is
    0.59
    t
    0.56
    u
    0.56
    现状
    0.55
    Currently
    0.55
    Activations Density 0.053%

    No Known Activations