© 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. 94816
    Prev
    Next
    INDEX
    Explanations

    plant products and oils

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

    plant diseases and diet

    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
    ালো
    0.73
     cavité
    0.69
     dług
    0.64
     práctico
    0.64
     büyü
    0.63
    ك
    0.63
     مرکز
    0.63
     keluarga
    0.62
     شکل
    0.62
     と
    0.61
    POSITIVE LOGITS
    '
    0.91
    ’
    0.91
    و
    0.88
    ak
    0.75
    ).
    0.72
    }.
    0.72
     Vegetables
    0.71
    ",
    0.70
     🌱
    0.70
    ind
    0.70
    Activations Density 0.271%

    No Known Activations