© 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. 199601
    Prev
    Next
    INDEX
    Explanations

    foreign technical terms

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

    physical or artificial environments

    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
    0.52
     Use
    0.51
    '
    0.47
    ;
    0.46
     Allows
    0.46
    "
    0.45
     User
    0.45
    member
    0.44
     Improve
    0.44
    ();
    0.43
    POSITIVE LOGITS
    拶
    0.50
     dévo
    0.50
     recién
    0.49
     météor
    0.49
    ungkap
    0.48
     meteorological
    0.48
     turbulence
    0.47
    の世界
    0.47
    भावस्था
    0.47
     phenomenology
    0.47
    Activations Density 0.001%

    No Known Activations