© 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. 152166
    Prev
    Next
    INDEX
    Explanations

    steel screws beside parameters

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

    background, history, variations

    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
    蝴
    0.55
    蛩
    0.54
    嗥
    0.48
    样子
    0.44
    潼
    0.44
    垕
    0.43
    говари
    0.42
     hippocampus
    0.40
    掮
    0.40
    聋
    0.40
    POSITIVE LOGITS
     sicurezza
    0.50
     جر
    0.50
     ٿ
    0.48
     riform
    0.48
     complesso
    0.48
    rystall
    0.48
    وني
    0.48
     Austrian
    0.47
     زين
    0.46
    setPreferredSize
    0.46
    Activations Density 0.001%

    No Known Activations