© 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. 113593
    Prev
    Next
    INDEX
    Explanations

    projects, people, cultures, or languages

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

    skills, projects, keywords

    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
    laš
    0.44
     Lett
    0.42
    導
    0.42
    ac
    0.41
     Mitochondrial
    0.40
    tenberg
    0.40
    um
    0.39
    詳細
    0.39
    maketitle
    0.39
     Brookhaven
    0.39
    POSITIVE LOGITS
     проекты
    0.54
    ﺒ
    0.52
     Аль
    0.52
     наблю
    0.52
     память
    0.52
     ар
    0.51
     culturas
    0.51
     ludzie
    0.50
     писать
    0.50
     паліты
    0.49
    Activations Density 0.000%

    No Known Activations