© 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. 13-GEMMASCOPE-2-RES-16K
    7. 12642
    Prev
    Next
    INDEX
    Explanations

    Okay, this is a

    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_13_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
    ;
    1.26
    :
    1.12
     (
    1.05
     hingegen
    0.97
    .
    0.96
     ise
    0.94
    (
    0.93
     соответственно
    0.93
     sie
    0.91
    ่
    0.90
    POSITIVE LOGITS
    甚至是
    1.71
    庣
    1.59
    ającej
    1.58
    峼
    1.55
    apetiti
    1.53
    𒁾
    1.53
    _{+}^{
    1.52
    軖
    1.52
    𒌵
    1.51
    chromiumfx
    1.51
    Activations Density 0.222%

    No Known Activations