© 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. 86746
    Prev
    Next
    INDEX
    Explanations

    heavy duty

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

    heavy descriptor

    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
    ین
    0.77
    々
    0.63
    ela
    0.61
     ecosystems
    0.61
    ە
    0.55
    ങ്ങൾ
    0.54
    ermanfaat
    0.54
     انسان
    0.53
     batas
    0.53
    し
    0.53
    POSITIVE LOGITS
     Heavy
    1.54
     heavy
    1.52
    Heavy
    1.47
    heavy
    1.44
     heavier
    1.41
     heaviest
    1.41
    重
    1.41
    重的
    1.34
     pesante
    1.32
     ভারী
    1.26
    Activations Density 0.076%

    No Known Activations