© 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. 810
    Prev
    Next
    INDEX
    Explanations

    negation and denial

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

    words meaning never or no

    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
     dives
    0.47
    难以
    0.45
     riesce
    0.42
    Consistency
    0.42
     достига
    0.42
     оптими
    0.42
    較
    0.42
    就需要
    0.41
     تساعد
    0.41
    较
    0.41
    POSITIVE LOGITS
     allegation
    0.64
     alleged
    0.63
     jamás
    0.63
     allegations
    0.63
     refuted
    0.62
     refute
    0.59
     전혀
    0.58
     rumor
    0.57
     rumour
    0.57
     rumours
    0.56
    Activations Density 0.164%

    No Known Activations