© 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. 13-GEMMASCOPE-2-RES-16K
    7. 14233
    Prev
    Next
    INDEX
    Explanations

    secure solutions

    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_13_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
     full
    1.07
     colds
    1.06
     холо
    1.04
     .
    1.02
     right
    1.01
     (
    0.97
     run
    0.96
     snow
    0.95
     l
    0.94
     air
    0.93
    POSITIVE LOGITS
    fNil
    1.51
    İR
    1.44
    <unused298>
    1.42
    GTBase
    1.42
    HasStarred
    1.42
    HDI
    1.40
    isOnTimer
    1.40
    ColumnKind
    1.40
    <unused1251>
    1.39
    <unused1635>
    1.39
    Activations Density 0.000%

    No Known Activations