© 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. 100895
    Prev
    Next
    INDEX
    Explanations

    shrove tuesday, apron, both

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

    bolded sections and ensuing phrases

    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
    Bran
    0.52
    ราย
    0.50
    ।--
    0.49
    Mord
    0.46
     справедливо
    0.46
    Bhar
    0.45
    ടതി
    0.45
    лени
    0.45
     діяльності
    0.45
     decisões
    0.44
    POSITIVE LOGITS
     b
    0.60
     d
    0.54
     texture
    0.51
    bc
    0.50
     m
    0.49
     {.
    0.49
    ó
    0.49
    phone
    0.48
    ys
    0.47
    uts
    0.47
    Activations Density 0.000%

    No Known Activations