© 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. 62523
    Prev
    Next
    INDEX
    Explanations

    minutes before

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

    institutional investors

    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
    Taxi
    0.48
    十七章
    0.46
    भंगा
    0.46
    ুরা
    0.46
    DropDown
    0.45
    是對
    0.44
    UnitTest
    0.44
    瀧
    0.43
    XXXXXXXX
    0.43
    ुरा
    0.43
    POSITIVE LOGITS
     ماما
    0.49
     biraz
    0.48
     ovales
    0.48
     mommy
    0.47
     pals
    0.47
     houve
    0.46
     prenant
    0.46
     aparato
    0.45
     aparelho
    0.45
     poema
    0.44
    Activations Density 0.000%

    No Known Activations