© 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. 16160
    Prev
    Next
    INDEX
    Explanations

    products and services

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

    energy and related concepts

    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
    ;
    0.47
    ?
    0.46
    MathOperator
    0.45
    兢
    0.44
    InterfaceLine
    0.44
    d
    0.41
    姬
    0.41
    졸
    0.41
    ่ย
    0.40
    ColumnHeaders
    0.40
    POSITIVE LOGITS
     उत्पाद
    0.50
     võimal
    0.48
     okam
    0.48
     coltiv
    0.48
     nitric
    0.47
     polyvinyl
    0.47
     hardcover
    0.47
     möj
    0.46
     kehad
    0.46
     assoc
    0.46
    Activations Density 0.000%

    No Known Activations