© 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. 233645
    Prev
    Next
    INDEX
    Explanations

    due date

    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
    ei
    0.53
    elt
    0.48
    驱
    0.46
     متاثر
    0.44
    lass
    0.43
    эй
    0.42
    verbose
    0.41
    glers
    0.40
    lere
    0.40
     elicit
    0.40
    POSITIVE LOGITS
    ಾನೆ
    0.53
     ښ
    0.51
     Dishes
    0.49
     BBBB
    0.49
     Freshman
    0.49
     Kear
    0.47
    ட
    0.47
     Zr
    0.47
     Nghi
    0.47
    湎
    0.46
    Activations Density 0.000%

    No Known Activations