© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 1751
    Prev
    Next
    INDEX
    Explanations

    appearing frequently

    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
     తప్ప
    1.69
    ా
    1.65
    sak
    1.62
    near
    1.59
    melt
    1.56
    sac
    1.55
     Occidental
    1.54
    ncc
    1.54
    Фи
    1.52
     subl
    1.50
    POSITIVE LOGITS
     focused
    1.74
    檚
    1.69
    orithms
    1.67
    gebnis
    1.57
     focuses
    1.54
    eting
    1.53
     focussed
    1.49
     Us
    1.47
    ɣ
    1.47
    __()
    1.46
    Activations Density 0.000%

    No Known Activations