© 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. 9521
    Prev
    Next
    INDEX
    Explanations

    details number flowers elusive poked

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

    theme / thematic

    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
    吳
    0.48
     ибо
    0.40
    ।...
    0.39
     γιατί
    0.39
    November
    0.38
    😔
    0.38
    நான்
    0.37
    敎
    0.37
    文學
    0.37
    ﺃ
    0.36
    POSITIVE LOGITS
     इन्हें
    0.51
     them
    0.50
     onboarding
    0.49
     tyto
    0.49
     details
    0.48
     these
    0.47
     इनको
    0.46
     updates
    0.45
     mutex
    0.45
     इन
    0.44
    Activations Density 0.001%

    No Known Activations