© 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. 96638
    Prev
    Next
    INDEX
    Explanations

    statistics regarding

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

    negation and exceptions

    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
     costes
    0.47
    fois
    0.46
     occasionally
    0.45
    祺
    0.45
    ভূতি
    0.44
    odenum
    0.44
     costi
    0.43
    iguation
    0.43
     costs
    0.43
     beautiful
    0.42
    POSITIVE LOGITS
     الذي
    0.47
    ην
    0.46
    ᄎ
    0.45
    生産
    0.44
    從
    0.43
     व्यंजन
    0.43
     कारवाई
    0.43
     وارد
    0.43
     Вулкан
    0.42
     ktorý
    0.42
    Activations Density 0.000%

    No Known Activations