© 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. 55721
    Prev
    Next
    INDEX
    Explanations

    local expertise

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

    ideas into, intersection of, challenge accepted

    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
    넴
    0.49
    νά
    0.44
    膜
    0.44
     vucc
    0.42
     cleansing
    0.42
     neum
    0.42
     getDescription
    0.42
     realistically
    0.41
     شہ
    0.41
    等方面
    0.41
    POSITIVE LOGITS
    Into
    0.55
    Ihr
    0.54
    Risk
    0.54
    ı
    0.51
    ut
    0.51
    alg
    0.50
    Calories
    0.50
    he
    0.49
    Anda
    0.49
    Lod
    0.49
    Activations Density 0.000%

    No Known Activations