© 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. 131481
    Prev
    Next
    INDEX
    Explanations

    discount, support, clue, reject

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

    golf driver

    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
    យៈ
    0.44
    hift
    0.43
     According
    0.41
    According
    0.40
    shooting
    0.40
     transistors
    0.40
    
    0.40
    每個
    0.40
     kultur
    0.39
    Sy
    0.39
    POSITIVE LOGITS
     남자
    0.47
    髂
    0.47
     நின்
    0.45
    抚
    0.45
    ībā
    0.44
    ிகளை
    0.44
    იც
    0.44
    ວ່າ
    0.44
     بیمار
    0.44
    만한
    0.43
    Activations Density 0.000%

    No Known Activations