© 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. 151115
    Prev
    Next
    INDEX
    Explanations

    official supplies Minecraft

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

    nouns and concepts

    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
    वाली
    0.46
     करण्यात
    0.46
     करवाना
    0.42
     Turki
    0.42
     Verein
    0.42
     moot
    0.42
     supaya
    0.41
    竅
    0.41
    SHO
    0.41
     त्याची
    0.41
    POSITIVE LOGITS
    क्स्ट
    0.47
     lectus
    0.46
     religiosos
    0.45
    牛仔
    0.45
     कांस्टेबल
    0.45
    手指
    0.43
     atleta
    0.43
     алге
    0.42
     tattooed
    0.42
     climbs
    0.41
    Activations Density 0.000%

    No Known Activations