© 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. 33263
    Prev
    Next
    INDEX
    Explanations

    learns, same, strong

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

    Soviet troops

    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
    Berat
    0.43
     Emirates
    0.42
    दाना
    0.41
     dê
    0.40
     अनुदान
    0.40
    랩
    0.40
    `:
    0.40
    দানের
    0.39
    Ậ
    0.39
    ính
    0.38
    POSITIVE LOGITS
     пище
    0.42
    ятся
    0.40
     Pandemic
    0.40
     Stochastic
    0.40
     degenerate
    0.39
    就需要
    0.39
     multifaceted
    0.38
     multicolored
    0.38
    եռ
    0.37
     মহামার
    0.37
    Activations Density 0.000%

    No Known Activations