© 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. 237334
    Prev
    Next
    INDEX
    Explanations

    online scheduling

    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
     kitty
    0.54
     feline
    0.50
     Mostly
    0.48
    躹
    0.48
    RationalValue
    0.48
    ಿಗಳು
    0.47
     들어
    0.47
     সদস্যদের
    0.46
     Alla
    0.46
     Ettha
    0.45
    POSITIVE LOGITS
    BC
    0.50
    -
    0.48
    鲨
    0.46
    Japan
    0.46
     enseñar
    0.45
    UT
    0.44
    INTRODUCTION
    0.44
    house
    0.43
    HK
    0.43
    Patent
    0.43
    Activations Density 0.000%

    No Known Activations