© 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. 11039
    Prev
    Next
    INDEX
    Explanations

    route definition in code

    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
    ഹ്ലാദ
    3.10
    紝
    3.08
    ี
    2.97
     corrid
    2.86
     convexes
    2.85
    煸
    2.75
    俬
    2.75
     wavelet
    2.74
    िखित
    2.71
    ributedString
    2.70
    POSITIVE LOGITS
    i
    3.73
    <bos>
    3.24
    yi
    2.86
    opia
    2.67
    yil
    2.58
    iop
    2.57
    人民政府
    2.51
    <code>
    2.50
    yse
    2.44
    물이
    2.39
    Activations Density 0.012%

    No Known Activations