© 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. 127732
    Prev
    Next
    INDEX
    Explanations

    extent, pain, affect, numbers, punctuation, here, iconic, UK

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

    local storage and drivers

    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
    ֣
    0.55
    睪
    0.48
    ف
    0.47
    را
    0.47
    멈
    0.46
    ރ
    0.46
    䡊
    0.46
    ชา
    0.46
    琢
    0.44
    燻
    0.44
    POSITIVE LOGITS
     durante
    0.54
     casado
    0.52
     počas
    0.51
    lere
    0.50
     pocos
    0.50
     dihasil
    0.48
     nascetur
    0.47
     licenci
    0.47
     interag
    0.47
     apenas
    0.46
    Activations Density 0.000%

    No Known Activations