© 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. 205497
    Prev
    Next
    INDEX
    Explanations

    structured text lists or explanations

    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
     Tây
    0.46
    Delta
    0.45
     ostensibly
    0.44
    קום
    0.42
    ↵
    0.42
    ↵↵
    0.42
     Naf
    0.41
    Rg
    0.41
     RESOURCES
    0.41
     NMR
    0.38
    POSITIVE LOGITS
    庿
    0.53
     इत्यादी
    0.52
     ه
    0.51
    ности
    0.51
    oarthritis
    0.50
    گیا
    0.50
    媇
    0.50
    NONE
    0.50
     久
    0.50
    neighbours
    0.49
    Activations Density 0.001%

    No Known Activations