© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 10381
    Prev
    Next
    INDEX
    Explanations

    extracting listing titles and names

    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
    Negative Logits
     współpr
    2.47
    ᆭ
    2.30
     นํา
    2.27
     hidrógeno
    2.27
    ['
    2.22
     tarafından
    2.19
    یشه
    2.18
    预
    2.17
     setCart
    2.17
    )'
    2.17
    POSITIVE LOGITS
     substantial
    2.61
     ominous
    2.41
     mundane
    2.26
     sinister
    2.21
     hefty
    2.21
     startled
    2.14
     sizable
    2.07
    ęs
    2.04
     eerie
    2.04
     picturesque
    2.03
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.