© 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. 10877
    Prev
    Next
    INDEX
    Explanations

    body parts and related actions

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

    body parts and sensations

    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
    とする
    0.57
    舩
    0.55
    quả
    0.55
    キャラクター
    0.54
    젊
    0.51
    বর্তমানে
    0.51
    রাজনৈতিক
    0.50
    𝓎
    0.50
    아버지
    0.50
    আমাদের
    0.49
    POSITIVE LOGITS
    -
    0.55
     twitch
    0.55
     tingling
    0.52
     ankles
    0.50
     ankle
    0.48
     toe
    0.47
    ↵
    0.47
     toes
    0.47
     screech
    0.47
     femur
    0.46
    Activations Density 0.065%

    No Known Activations