© 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. 31-GEMMASCOPE-2-RES-262K
    7. 12738
    Prev
    Next
    INDEX
    Explanations

    schedule or tasks

    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
    0.60
     in
    0.52
     the
    0.51
     (
    0.50
     to
    0.49
      
    0.47
     a
    0.46
     one
    0.46
     end
    0.44
     can
    0.44
    POSITIVE LOGITS
    玖章
    0.44
    GEBURTS
    0.43
    𒅴
    0.42
     bottlene
    0.42
     للمعارف
    0.41
     गिवन
    0.41
    getBlueTeam
    0.41
    ╽
    0.41
     CustB
    0.40
    urètre
    0.40
    Activations Density 0.000%

    No Known Activations