© 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. 225437
    Prev
    Next
    INDEX
    Explanations

    writing, also Simplify

    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
     ciudadano
    0.48
     schnelle
    0.46
     rozší
    0.45
    ரூராட்சி
    0.44
     wenige
    0.44
    ideos
    0.43
    citizen
    0.43
    𝙣
    0.43
     tyto
    0.43
    নির্দিষ্ট
    0.43
    POSITIVE LOGITS
     (
    0.56
     του
    0.50
     اجازه
    0.49
     Spectacular
    0.46
     reasoning
    0.45
     او
    0.43
     Ο
    0.43
     ఎ
    0.43
     υ
    0.43
    ement
    0.43
    Activations Density 0.001%

    No Known Activations