© 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. 2856
    Prev
    Next
    INDEX
    Explanations

    descriptive contexts for dark themes

    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
    ΙΚ
    1.73
    sız
    1.71
    va
    1.70
    ر
    1.68
    رین
    1.65
     intensification
    1.65
    ral
    1.62
    azes
    1.55
    lost
    1.55
    ry
    1.55
    POSITIVE LOGITS
    eture
    2.38
    瓈
    2.18
     файла
    2.10
     тих
    2.01
     Ausgang
    1.99
    Utc
    1.99
    洎
    1.97
    cology
    1.92
    etzen
    1.92
    ikiran
    1.91
    Activations Density 0.261%

    No Known Activations