© 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. 109395
    Prev
    Next
    INDEX
    Explanations

    having said, contrast to, lifestyle documentary

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

    building ideas with options

    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
     infuse
    0.51
     retirer
    0.48
     elevate
    0.48
     createFile
    0.48
     hoera
    0.45
     খুন
    0.45
     নগ
    0.44
    蝌
    0.44
     gooey
    0.43
     fonctionnal
    0.43
    POSITIVE LOGITS
     и
    0.47
    в
    0.47
    Ὁ
    0.46
    都有
    0.46
     Galbraith
    0.46
     Unpublished
    0.44
     Baran
    0.44
    万
    0.44
    mode
    0.44
    unpublished
    0.44
    Activations Density 0.000%

    No Known Activations