© 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. 80764
    Prev
    Next
    INDEX
    Explanations

    allow time, consistently fails, relatively light

    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
    Negative Logits
     slump
    0.48
    )$-
    0.46
    ঘর
    0.46
     shoulder
    0.45
    ナイ
    0.45
    फिक
    0.44
    ']*
    0.44
    dienst
    0.44
    ד
    0.44
     racket
    0.44
    POSITIVE LOGITS
    ished
    0.46
     ebbe
    0.42
     плате
    0.42
    <unused61>
    0.41
    只会
    0.41
     vices
    0.40
     ലീ
    0.40
    èr
    0.40
    o
    0.39
    at
    0.39
    Activations Density 0.000%

    No Known Activations