© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 32986
    Prev
    Next
    INDEX
    Explanations

    mentions and identifiers starting with @

    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_40_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
     선생
    0.41
    =\"
    0.40
    __________
    0.40
    \"
    0.39
    ĩ
    0.38
    
    0.36
    ﱠ
    0.36
    \"{
    0.36
    '].'
    0.35
    朼
    0.35
    POSITIVE LOGITS
     @
    2.73
    @
    2.17
     `@
    2.13
     (@
    2.02
    (@
    1.96
     @_
    1.94
     "@
    1.93
    ,@
    1.91
    :@
    1.88
     '@
    1.85
    Activations Density 0.012%

    No Known Activations