© 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. 132867
    Prev
    Next
    INDEX
    Explanations

    work with

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

    square root and tracking

    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
    ка
    0.63
    買い物
    0.59
    та
    0.55
    Фото
    0.53
    ソフトウェア
    0.52
    су
    0.50
     Кри
    0.50
    ซ
    0.50
     Galleria
    0.49
    рей
    0.49
    POSITIVE LOGITS
    t
    0.61
    y
    0.54
    tio
    0.53
    ei
    0.51
    undle
    0.48
    órica
    0.48
     detonations
    0.48
     espiritual
    0.48
    s
    0.47
    iolet
    0.47
    Activations Density 0.000%

    No Known Activations