© 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. 179577
    Prev
    Next
    INDEX
    Explanations

    hand or hands

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

    handle

    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
     (
    0.72
    al
    0.59
    ing
    0.55
    ೇ
    0.52
     myster
    0.49
     Usage
    0.49
     Musicians
    0.48
    ali
    0.47
     I
    0.47
     registr
    0.46
    POSITIVE LOGITS
    자
    0.68
    手を
    0.66
    ất
    0.64
    국
    0.59
    ığı
    0.58
    ᱗
    0.57
    手の
    0.57
    手
    0.56
    下に
    0.55
    ため
    0.55
    Activations Density 0.000%

    No Known Activations