© 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. 101653
    Prev
    Next
    INDEX
    Explanations

    American first African American

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

    positive relationships and communication

    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
     Inst
    0.53
     exceeding
    0.50
     instabilities
    0.50
     युवा
    0.43
    ো
    0.43
     instability
    0.43
     cataracts
    0.43
     sportswear
    0.41
     pests
    0.40
     اسی
    0.40
    POSITIVE LOGITS
     dupa
    0.53
    鼠标
    0.52
    してる
    0.47
    你要
    0.46
     November
    0.46
     octobre
    0.46
    }^{(
    0.46
     хочет
    0.46
     希望
    0.46
    ㈤
    0.45
    Activations Density 0.000%

    No Known Activations