© 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. 40-GEMMASCOPE-2-RES-65K
    7. 52715
    Prev
    Next
    INDEX
    Explanations

    using hands or fingers

    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_40_width_65k_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
     chest
    0.54
     neck
    0.52
     thorax
    0.52
     torso
    0.50
     tubuh
    0.49
     rambut
    0.48
    Neck
    0.48
    颈
    0.48
     neckline
    0.47
     Körper
    0.47
    POSITIVE LOGITS
     hands
    1.04
    hands
    1.01
    Hands
    0.91
    手
    0.86
     fingers
    0.85
     hand
    0.84
     Hands
    0.83
    มือ
    0.80
    手を
    0.80
     tangan
    0.80
    Activations Density 0.053%

    No Known Activations