© 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. 11504
    Prev
    Next
    INDEX
    Explanations

    could not retrieve or read

    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
    Kisi
    2.43
    PickerController
    2.35
    achim
    2.30
    覦
    2.12
    setPreferredSize
    2.08
     parámetro
    2.07
     perturbed
    2.04
    Supreme
    2.01
    Fantasy
    2.00
     fichero
    1.98
    POSITIVE LOGITS
    ्स
    2.95
    alink
    2.39
    ्ट
    2.29
    م
    2.26
    ILITY
    2.07
    lucent
    2.06
    namese
    2.02
    mire
    2.01
    തിനുള്ള
    1.99
    uell
    1.98
    Activations Density 0.471%

    No Known Activations