© 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. 89661
    Prev
    Next
    INDEX
    Explanations

    data completeness accuracy

    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
     vollständig
    0.46
    +(\
    0.46
    녘
    0.44
    ◌
    0.43
    šen
    0.42
    ologisch
    0.42
    ဍ
    0.41
    BEN
    0.41
    usten
    0.41
    ළු
    0.40
    POSITIVE LOGITS
     (
    0.59
    ifiques
    0.52
     occup
    0.50
     conditions
    0.50
     during
    0.50
     disorders
    0.50
     pond
    0.49
     Mall
    0.49
     attire
    0.49
     headway
    0.49
    Activations Density 0.001%

    No Known Activations