© 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. 172538
    Prev
    Next
    INDEX
    Explanations

    all-inclusive package

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

    text negation in multiple languages

    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
    andet
    0.54
    h
    0.54
    %
    0.53
    ds
    0.52
    ns
    0.50
     verden
    0.50
    att
    0.50
    hir
    0.50
    stvo
    0.49
    hs
    0.49
    POSITIVE LOGITS
    ौदा
    0.50
    葡
    0.48
    きた
    0.48
    ូង
    0.48
    煖
    0.46
    後の
    0.46
     huynh
    0.45
     ওসমান
    0.44
     यानि
    0.44
     নিম
    0.44
    Activations Density 0.000%

    No Known Activations