© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 3830
    Prev
    Next
    INDEX
    Explanations

    efficacy of treatments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_width_16k_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
    רות
    2.77
    ｍｍ
    2.63
    𝑠
    2.42
     طریقے
    2.42
    Ｏ
    2.38
    Ｆ
    2.35
     względu
    2.34
    बीएसई
    2.29
    anyard
    2.27
     ایکس
    2.27
    POSITIVE LOGITS
    ت
    3.33
    تهم
    3.13
    ty
    2.41
    ക്കുറിച്ച്
    2.37
    ़
    2.33
    ക്കുറിച്ച
    2.24
    TERS
    2.21
    tede
    2.18
    los
    2.18
    י
    2.17
    Activations Density 0.061%

    No Known Activations