© 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. 50482
    Prev
    Next
    INDEX
    Explanations

    what if

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

    Why choose, reveal vulnerabilities, lost

    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
    ﮅ
    0.54
     സൂര്യ
    0.46
     seguenti
    0.46
     következő
    0.45
    يزة
    0.45
     allegations
    0.45
     नवे
    0.45
     അയാള
    0.45
     เขา
    0.44
     അപകട
    0.44
    POSITIVE LOGITS
    dB
    0.47
    ᾶ
    0.46
    inv
    0.44
     reverber
    0.43
     кирпи
    0.43
    党
    0.42
     форме
    0.42
    филь
    0.41
    cedor
    0.41
    клю
    0.41
    Activations Density 0.000%

    No Known Activations