© 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. 75435
    Prev
    Next
    INDEX
    Explanations

    observable signs of change

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

    personal descriptions and abstract concepts

    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
     VERY
    0.45
    는
    0.43
    이라고
    0.41
    )。
    0.41
    Ĺ
    0.40
    рев
    0.40
     meget
    0.40
     veľmi
    0.39
    엣
    0.39
    very
    0.39
    POSITIVE LOGITS
    BUSINESS
    0.47
     مما
    0.45
     הק
    0.45
     needlessly
    0.45
    Polling
    0.45
     স্কুল
    0.45
    淑
    0.44
    Jy
    0.44
     wilfully
    0.44
     stubbornly
    0.44
    Activations Density 0.001%

    No Known Activations