© 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-3-270M
    5. 12-GEMMASCOPE-2-RES-16K
    7. 6663
    Prev
    Next
    INDEX
    Explanations

    locations following the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_12_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
     elecciones
    1.70
    rarea
    1.66
     cómo
    1.65
     crucible
    1.65
    ≐
    1.64
     empleo
    1.62
     Kippur
    1.61
     lavoro
    1.60
     Schumer
    1.59
     정도로
    1.58
    POSITIVE LOGITS
    önes
    1.43
    jazd
    1.37
     redirects
    1.30
    Foreground
    1.26
    ถม
    1.19
     centrally
    1.17
    foreground
    1.14
     南
    1.14
    ...@
    1.13
    sides
    1.09
    Activations Density 0.121%

    No Known Activations