© 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. 174850
    Prev
    Next
    INDEX
    Explanations

    raising money and support

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

    content disclaimers

    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
     both
    0.46
    溘
    0.46
     aswell
    0.45
     Research
    0.45
     matern
    0.44
     matrícula
    0.44
     Forbes
    0.44
     USDA
    0.43
     Older
    0.43
    찬
    0.43
    POSITIVE LOGITS
    érable
    0.45
    omena
    0.44
     परिस्थिती
    0.44
     श्रृंखला
    0.44
     কিছুর
    0.43
    zego
    0.43
     लक्ष्मण
    0.43
     리그
    0.42
     இதுவரை
    0.42
    zuat
    0.42
    Activations Density 0.001%

    No Known Activations