© 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. 40-GEMMASCOPE-2-RES-16K
    7. 9147
    Prev
    Next
    INDEX
    Explanations

    fasteners and bindings

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

    rope and cable

    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_40_width_16k_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
     ট্যাবলেট
    0.47
    tablet
    0.47
     табле
    0.46
     createArticle
    0.44
    剜
    0.44
     APIDC
    0.43
    龕
    0.43
    砒
    0.42
    𒀊
    0.42
     viewBox
    0.41
    POSITIVE LOGITS
     rope
    1.98
     Rope
    1.84
     ropes
    1.84
    绳
    1.79
    繩
    1.72
     dây
    1.64
     cables
    1.57
    rope
    1.55
     cable
    1.55
     रस्सी
    1.53
    Activations Density 0.607%

    No Known Activations