© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 82678
    Prev
    Next
    INDEX
    Explanations

    items out of

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

    consistent mood impact

    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
    Negative Logits
     May
    0.51
     October
    0.50
    ında
    0.49
     November
    0.49
     IEEE
    0.49
     JANUARY
    0.47
    ḥ
    0.47
    ğe
    0.46
     January
    0.46
     européen
    0.46
    POSITIVE LOGITS
    색
    0.48
     cardiomyopathy
    0.46
     פס
    0.45
     الاستفهام
    0.45
    账
    0.45
     자신이
    0.45
    それ
    0.45
    そんな
    0.45
    갤
    0.44
     ና
    0.43
    Activations Density 0.000%

    No Known Activations