© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 11500
    Prev
    Next
    INDEX
    Explanations

    negation or exclusion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ştik
    0.37
    нів
    0.36
    এন
    0.36
     சில
    0.35
    enders
    0.35
    杫
    0.34
    <unused398>
    0.34
    ுகளை
    0.34
    คนที่
    0.34
    ଙ
    0.34
    POSITIVE LOGITS
     alcuna
    0.64
     quelconque
    0.61
     alcun
    0.54
     quelcon
    0.53
     ningún
    0.52
     żad
    0.52
     neither
    0.49
     nenhuma
    0.48
     nenhum
    0.45
     никакого
    0.45
    Activations Density 0.417%

    No Known Activations