© 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. 10442
    Prev
    Next
    INDEX
    Explanations

    competitive speedrunning

    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
     '),
    1.80
     Тимо
    1.79
    ាទ
    1.75
     textBox
    1.64
    پا
    1.61
     Сте
    1.60
    رحله
    1.58
    篁
    1.58
     گ
    1.58
     initializes
    1.57
    POSITIVE LOGITS
     dazz
    1.59
    issuer
    1.55
    bending
    1.52
     shackles
    1.47
    ichtet
    1.46
    talent
    1.43
    bend
    1.41
    nment
    1.40
    bokeh
    1.39
     aesthetics
    1.39
    Activations Density 0.000%

    No Known Activations