© 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. 39966
    Prev
    Next
    INDEX
    Explanations

    body and body parts

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

    html head closing tag

    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
    ною
    0.38
    irteen
    0.38
    για
    0.38
    媢
    0.38
     স্টি
    0.38
     Rock
    0.37
     фаразлау
    0.37
    BtnUp
    0.37
    坵
    0.37
     रहें
    0.36
    POSITIVE LOGITS
    body
    0.64
    <body>
    0.61
     body
    0.61
     bod
    0.56
     bodied
    0.54
     BODY
    0.52
     몸
    0.50
     الجسم
    0.49
    bodies
    0.48
     thân
    0.47
    Activations Density 0.011%

    No Known Activations