© 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. 12660
    Prev
    Next
    INDEX
    Explanations

    phases or weeks

    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
    range
    1.41
    awa
    1.38
    oda
    1.34
    obil
    1.25
     hablamos
    1.25
    ल्हे
    1.25
    جيل
    1.25
    征
    1.25
    žal
    1.24
    时刻
    1.23
    POSITIVE LOGITS
     сами
    1.73
     бло
    1.46
     препаратов
    1.41
     молоды
    1.40
     tutorials
    1.40
     methodologies
    1.39
     тар
    1.38
     самим
    1.37
     фо
    1.36
     peripherals
    1.36
    Activations Density 0.000%

    No Known Activations