© 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. 178873
    Prev
    Next
    INDEX
    Explanations

    teaching labs

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

    God, light, most people

    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
    List
    0.53
    Summary
    0.46
    publishing
    0.46
    녠
    0.46
     Summary
    0.45
    Moment
    0.45
    Face
    0.44
    Assertion
    0.43
    getResources
    0.43
     налич
    0.43
    POSITIVE LOGITS
    辐
    0.52
     piezo
    0.52
    輻
    0.49
     piezoelectric
    0.48
     raíz
    0.47
    squre
    0.46
     جریان
    0.45
     beispielsweise
    0.44
    辐射
    0.44
     ப்
    0.44
    Activations Density 0.000%

    No Known Activations