© 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. 57490
    Prev
    Next
    INDEX
    Explanations

    latest versions

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

    Password or suffix requirements

    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
    дные
    0.52
     Contain
    0.48
    獲
    0.45
    ᄎ
    0.45
    ᄅ
    0.44
     paj
    0.44
    Ռ
    0.43
    ট্র
    0.43
    ᄌ
    0.43
    䉽
    0.42
    POSITIVE LOGITS
     postage
    0.41
     μό
    0.38
    Browser
    0.37
    terminal
    0.36
     receptionist
    0.36
     oldu
    0.36
     browser
    0.36
    Git
    0.36
    sidebar
    0.35
    galkan
    0.35
    Activations Density 0.000%

    No Known Activations