© 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. 72102
    Prev
    Next
    INDEX
    Explanations

    local

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

    explicitly remind, risk, molecules, prompting

    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
    ﺳ
    0.54
    ینک
    0.51
     لیکن
    0.49
     sondern
    0.48
    skine
    0.47
    watch
    0.46
     nhưng
    0.46
     lắp
    0.46
     चढ
    0.44
    klich
    0.44
    POSITIVE LOGITS
    苇
    0.46
    ز
    0.45
    拂
    0.45
    gående
    0.44
    д
    0.44
    ัท
    0.43
    ات
    0.43
    Materials
    0.43
     Emerald
    0.43
    Emerald
    0.43
    Activations Density 0.001%

    No Known Activations