© 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. 17386
    Prev
    Next
    INDEX
    Explanations

    foreign language or specific phrases

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

    code comments and instructions

    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
    телни
    0.45
    เ
    0.45
    ியா
    0.41
    ویی
    0.41
     projection
    0.41
    ,
    0.40
     targets
    0.39
     lifting
    0.39
     multiplier
    0.39
    다
    0.38
    POSITIVE LOGITS
    runoff
    0.54
     διαφο
    0.54
     سك
    0.54
     अस्त
    0.53
     जटिल
    0.53
     બધા
    0.52
    Todas
    0.52
    pessoa
    0.52
     complejos
    0.52
    ightly
    0.51
    Activations Density 0.000%

    No Known Activations