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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 4639
    Prev
    Next
    INDEX
    Explanations

    no / negation

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

    negations 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_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
    朤
    0.38
    संहार
    0.38
    큽
    0.35
     depending
    0.33
    ធ្វ
    0.33
    вест
    0.32
    粛
    0.31
    рович
    0.30
    쨋
    0.30
    肃
    0.30
    POSITIVE LOGITS
     no
    4.63
    no
    3.66
     No
    3.39
    No
    3.39
     NO
    3.28
    NO
    2.75
     keine
    2.59
     nobody
    2.38
     kein
    2.38
    ไม่มี
    2.38
    Activations Density 0.903%

    No Known Activations