© 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. 132579
    Prev
    Next
    INDEX
    Explanations

    workers providedisposal regardingabsolutely freetests

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

    features, modules, source, benefits

    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
    I
    0.61
     monitors
    0.55
    t
    0.53
    tion
    0.51
     vint
    0.50
     mod
    0.50
     toys
    0.49
     nanotechnology
    0.49
     for
    0.49
     by
    0.49
    POSITIVE LOGITS
    м
    0.57
    的基本
    0.52
    ariam
    0.51
    的需求
    0.49
    дный
    0.48
     Держа
    0.47
    рованной
    0.47
    Jogador
    0.47
    getEstado
    0.47
     વધ
    0.46
    Activations Density 0.000%

    No Known Activations