© 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
    2. Gemma-3-1B
    3. 7-GEMMASCOPE-2-RES-16K
    4. 3373
    Prev
    Next
    INDEX
    Explanations

    diagnostic manual (DSM)

    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
    is
    1.79
    в
    1.57
    at
    1.48
     (
    1.42
    jects
    1.40
     [
    1.33
    as
    1.33
    ़
    1.32
    Is
    1.30
    Intermediate
    1.29
    POSITIVE LOGITS
     décès
    2.39
     réellement
    2.33
     différences
    2.31
     IUnary
    2.26
     elytris
    2.25
    𒊶
    2.24
     getSchema
    2.22
    <unused1399>
    2.21
    <unused1968>
    2.21
    𐱃
    2.21
    Activations Density 0.089%

    No Known Activations