© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 4107
    Prev
    Next
    INDEX
    Explanations

    Object Class

    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_all/layer_41_width_262k_l0_big
    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
    <unused59>
    0.45
     सुष
    0.43
     कटोच
    0.41
     ईमित्र
    0.41
    ibalsan
    0.41
    ྱ
    0.40
    ئی
    0.40
    миз
    0.40
    clone
    0.39
     clone
    0.38
    POSITIVE LOGITS
     Balkan
    0.36
     Boutique
    0.36
      
    0.35
     commitment
    0.35
     papers
    0.35
     retained
    0.35
     men
    0.35
     receive
    0.34
     Document
    0.34
     Argument
    0.34
    Activations Density 0.001%

    No Known Activations