© 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. 36237
    Prev
    Next
    INDEX
    Explanations

    negation, absence of something

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

    detecting negation

    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
     conveniences
    0.45
     ONLY
    0.44
    ସ
    0.44
     uniquement
    0.43
     automobiles
    0.42
     garantizar
    0.42
    ফ
    0.42
     innymi
    0.42
     without
    0.41
     accuracies
    0.41
    POSITIVE LOGITS
     hề
    0.54
    々は
    0.49
     دچار
    0.47
     會
    0.44
    docker
    0.44
     වෙන
    0.44
     rischi
    0.42
    FileURL
    0.42
     は
    0.41
     риск
    0.41
    Activations Density 0.157%

    No Known Activations