© 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. 157285
    Prev
    Next
    INDEX
    Explanations

    connecting through ports

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

    incorrect statements and grammar

    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
    本书
    0.56
     Tiktok
    0.48
     TikTok
    0.47
     disseminate
    0.45
     Discuss
    0.44
     Gentleman
    0.44
    ujukan
    0.44
    K
    0.44
    u
    0.44
     Verbal
    0.42
    POSITIVE LOGITS
     efficiencies
    0.52
    記念
    0.52
    investissement
    0.52
    投資
    0.50
     বিনিয়োগ
    0.50
    residents
    0.50
    付出
    0.50
    徒歩
    0.49
    誕生
    0.48
     residents
    0.47
    Activations Density 0.001%

    No Known Activations