© 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. 2820
    Prev
    Next
    INDEX
    Explanations

    passionate enthusiasm and fantasy

    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
     considéré
    2.45
    κο
    2.42
    ⃛
    2.39
     pavimento
    2.33
     oed
    2.31
     disimpan
    2.30
    transfected
    2.30
    élément
    2.29
     constitución
    2.28
    𝘵
    2.26
    POSITIVE LOGITS
    u
    3.17
    en
    3.01
    y
    2.98
    i
    2.87
    a
    2.85
    ی
    2.76
    r
    2.74
    ar
    2.72
    us
    2.63
    o
    2.62
    Activations Density 0.212%

    No Known Activations