© 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. 239164
    Prev
    Next
    INDEX
    Explanations

    OPERATIONS INC

    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
    зона
    0.54
    ืม
    0.53
    风景
    0.46
     ungdom
    0.46
    화
    0.44
    ᠮ
    0.44
    isiones
    0.43
    징
    0.43
    ᠬ
    0.43
    މ
    0.42
    POSITIVE LOGITS
     tra
    0.55
     regulate
    0.54
     param
    0.52
     biocompat
    0.51
     negligible
    0.51
     clickable
    0.50
     precarious
    0.50
     perf
    0.49
     regulator
    0.49
     bipart
    0.48
    Activations Density 0.001%

    No Known Activations