© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 1846
    Prev
    Next
    INDEX
    Explanations

    past and continuing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ون
    0.52
    ADA
    0.49
    (
    0.49
    Tasks
    0.48
    ↵↵
    0.45
    perature
    0.45
     ташки
    0.45
    upo
    0.43
    นั้น
    0.42
    verage
    0.42
    POSITIVE LOGITS
     chopsticks
    0.48
    št
    0.47
     இவர்
    0.45
     metres
    0.44
     visión
    0.44
     theseKeys
    0.44
     வள்ளி
    0.43
     இந்ந
    0.42
    ᆫ
    0.42
     mètres
    0.42
    Activations Density 0.000%

    No Known Activations