© 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. 104127
    Prev
    Next
    INDEX
    Explanations

    concessions and profits

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

    costs or promising results

    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
     這個
    0.58
    在他的
    0.53
    RectangleShape
    0.53
     ร
    0.51
     פ
    0.51
    兒童
    0.50
    Cohen
    0.50
    BackgroundColor
    0.50
     來
    0.49
     пр
    0.49
    POSITIVE LOGITS
     concessions
    0.49
     profits
    0.47
     concession
    0.47
     Profits
    0.47
     arrangements
    0.46
     dew
    0.43
    yty
    0.43
    antoin
    0.43
    etiti
    0.42
     stipulations
    0.42
    Activations Density 0.000%

    No Known Activations