© 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. 48302
    Prev
    Next
    INDEX
    Explanations

    questions and headings

    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
    0.48
    pulsewidth
    0.45
    핀
    0.44
    Bold
    0.43
     angegeben
    0.43
    грани
    0.43
    FrameLength
    0.43
    кнове
    0.43
    дав
    0.42
    ありがとうございました
    0.42
    POSITIVE LOGITS
     측
    0.48
     pathologies
    0.48
     hierarchies
    0.48
     種
    0.48
     मनो
    0.47
     rmse
    0.47
     கொலை
    0.47
     সংশ
    0.46
    បំ
    0.46
     नमी
    0.45
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.