© 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. 1647
    Prev
    Next
    INDEX
    Explanations

    Do you want to know

    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
    Never
    1.76
     NEVER
    1.73
    <unused722>
    1.72
    <unused708>
    1.71
     Never
    1.69
    <unused321>
    1.68
    栦
    1.68
    NoStop
    1.65
    <unused318>
    1.65
     aldrig
    1.65
    POSITIVE LOGITS
     some
    1.31
     might
    1.24
     (
    1.15
     may
    1.11
     برخی
    1.09
    some
    1.07
     you
    1.04
     a
    1.01
     certain
    1.00
     but
    0.99
    Activations Density 0.734%

    No Known Activations