© 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. 6698
    Prev
    Next
    INDEX
    Explanations

    incorporated by reference, Rights Reserved

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

    helpful AI

    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
     συγκεκρι
    0.33
    :
    0.31
     PUBL
    0.31
     Sharon
    0.29
     Hawaii
    0.29
     Johnny
    0.29
     শক্তিশালী
    0.29
     Michelle
    0.29
     einzelnen
    0.28
     বসবাস
    0.28
    POSITIVE LOGITS
    ר
    0.32
    제로
    0.30
    환
    0.30
    ↵↵↵
    0.30
    ு
    0.30
     부탁
    0.29
    드
    0.29
    백
    0.29
    썰
    0.29
    夺
    0.29
    Activations Density 0.105%

    No Known Activations