© 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. 36232
    Prev
    Next
    INDEX
    Explanations

    completion of this

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

    repeated calculations, specific tasks, aid

    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
    家
    0.52
     impactful
    0.52
    秋冬
    0.46
    <strong>
    0.46
    €
    0.46
    コ
    0.45
    igraf
    0.45
    爸
    0.44
     solide
    0.44
    靶
    0.44
    POSITIVE LOGITS
     Darstellung
    0.50
     occasioned
    0.48
     Demonstration
    0.48
     peculiarly
    0.47
     Commerce
    0.44
     nCurrent
    0.43
     Addresses
    0.43
     আদৌ
    0.43
     this
    0.43
     Cette
    0.42
    Activations Density 0.000%

    No Known Activations