© 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. 28326
    Prev
    Next
    INDEX
    Explanations

    concepts and definitions

    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
     विरु
    0.45
    icel
    0.45
    iteks
    0.44
    icions
    0.44
    ме
    0.43
    idak
    0.43
    📵
    0.42
    ंसर
    0.42
    ెం
    0.40
    및
    0.40
    POSITIVE LOGITS
     există
    0.48
     těchto
    0.46
     exist
    0.46
     العربي
    0.45
    这一点
    0.44
     parámetro
    0.43
    these
    0.43
     Yadav
    0.43
     Beg
    0.42
     ያስፈል
    0.42
    Activations Density 0.000%

    No Known Activations