© 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. 202563
    Prev
    Next
    INDEX
    Explanations

    we strive; we defended

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

    YAML, Pandas, file, DataFrame, Oven, license, February

    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
    ئات
    0.48
     waged
    0.48
    <0x11>
    0.47
     ਲੈ
    0.47
    vants
    0.47
    ತ್ಮ
    0.46
     mandib
    0.46
     fatores
    0.46
     săn
    0.46
    uesthouse
    0.45
    POSITIVE LOGITS
    um
    0.58
    бу
    0.51
    广
    0.49
    SG
    0.48
    hex
    0.46
    ou
    0.45
    ite
    0.45
    Geme
    0.45
     FIXME
    0.45
    Printer
    0.44
    Activations Density 0.001%

    No Known Activations