© 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. 111815
    Prev
    Next
    INDEX
    Explanations

    election outcomes and chief ministers

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

    chief minister or prime minister

    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
     américaine
    0.46
     USPS
    0.45
     détecter
    0.45
     ರಾಷ್ಟ
    0.45
    邰
    0.45
     président
    0.44
    配達
    0.43
     américain
    0.43
     américains
    0.42
     postal
    0.42
    POSITIVE LOGITS
     মুখ্যমন্ত্রী
    0.49
     മുഖ്യമന്ത്രി
    0.47
    peč
    0.44
     MLAs
    0.44
    ipel
    0.43
    मुख्यमंत्री
    0.43
    跪
    0.43
    endev
    0.42
    IPL
    0.42
    ijl
    0.42
    Activations Density 0.025%

    No Known Activations