© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 3130
    Prev
    Next
    INDEX
    Explanations

    point and its context

    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
    ്ര
    3.05
    eram
    2.99
     הור
    2.75
    ançois
    2.68
    ྩ
    2.61
    banners
    2.60
    гө
    2.58
    mazione
    2.56
    idene
    2.55
     cánh
    2.54
    POSITIVE LOGITS
    ↵↵↵↵↵↵↵↵
    2.37
    lighting
    2.28
    ''
    2.26
    heastern
    2.25
    urbo
    2.24
     ''
    2.21
    تقاوى
    2.21
     Ngf
    2.21
    ,''
    2.19
    -----
    2.18
    Activations Density 0.092%

    No Known Activations