© 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. 99629
    Prev
    Next
    INDEX
    Explanations

    overall performance

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

    African citizenship, activity

    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
     други
    0.53
     drugi
    0.49
     היה
    0.49
     vamos
    0.48
     השני
    0.48
    ).}
    0.48
    ление
    0.48
     suivie
    0.47
     việc
    0.47
     كان
    0.47
    POSITIVE LOGITS
    tel
    0.50
    吕
    0.47
    ü
    0.47
    alu
    0.47
    겔
    0.45
    ర
    0.44
    ai
    0.44
    ali
    0.44
    alar
    0.44
    alui
    0.44
    Activations Density 0.001%

    No Known Activations