© 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. 154953
    Prev
    Next
    INDEX
    Explanations

    follow up / create / send

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

    increased risk or UDP use

    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
     परिश
    0.56
    sofar
    0.55
    lush
    0.45
    in
    0.44
    роки
    0.43
     рассчита
    0.43
    <unused985>
    0.43
    includes
    0.43
     самом
    0.42
     исти
    0.42
    POSITIVE LOGITS
    ンの
    0.47
     clientele
    0.45
    ต้อง
    0.45
    lectoral
    0.43
    《
    0.43
    ช่อง
    0.42
     facie
    0.42
     citizenry
    0.42
    幣
    0.42
    ę
    0.41
    Activations Density 0.000%

    No Known Activations