© 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
    5. 53-GEMMASCOPE-2-RES-65K
    7. 8620
    Prev
    Next
    INDEX
    Explanations

    non- prefix negations

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

    non-consensual

    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_53_width_65k_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
    -;
    0.46
     pareil
    0.44
     Plusieurs
    0.42
    \-
    0.40
    -"
    0.39
     таки
    0.39
     আক্রমণ
    0.38
    posable
    0.37
    -,
    0.37
    னும்
    0.37
    POSITIVE LOGITS
     unforeseen
    0.51
     favourable
    0.48
     megfelel
    0.48
     unanticipated
    0.45
     favorable
    0.44
     planned
    0.44
     ভালোভাবে
    0.43
    planned
    0.43
     unexpected
    0.42
    unexpected
    0.42
    Activations Density 0.027%

    No Known Activations