© 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. 28449
    Prev
    Next
    INDEX
    Explanations

    online options and information

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

    contained herein

    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
     Verwendung
    0.47
     گیا۔
    0.40
     використання
    0.37
    ौड़
    0.37
     خش
    0.36
    役
    0.36
     derivada
    0.35
    قية
    0.35
     дали
    0.35
    だったら
    0.35
    POSITIVE LOGITS
     academia
    0.47
     ,
    0.38
     encontrarás
    0.36
     palettes
    0.36
    dst
    0.36
    ಳೆದ
    0.36
    declaration
    0.36
    nox
    0.35
    რე
    0.34
    fahren
    0.34
    Activations Density 0.068%

    No Known Activations