© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 195869
    Prev
    Next
    INDEX
    Explanations

    dinner, night, or leak

    np_acts-logits-general · gemini-2.5-flash-lite

    changes, damage, conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     मोटे
    0.56
    𝘼
    0.54
     жё
    0.53
    𝙝
    0.53
     μαύ
    0.52
     ഐ
    0.50
    ̉a
    0.50
     과거
    0.50
    యిత
    0.50
    𝘣
    0.49
    POSITIVE LOGITS
     simulation
    0.46
     sedimentation
    0.46
     people
    0.43
     evaporator
    0.42
     Don
    0.42
     purpose
    0.42
     satiety
    0.42
     Bryant
    0.41
     ingredient
    0.41
     Simulate
    0.41
    Activations Density 0.000%

    No Known Activations