© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 965
    Prev
    Next
    INDEX
    Explanations

    formatting and structure

    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_22_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
     Worcestershire
    0.75
     yath
    0.73
     (£
    0.73
    kes
    0.71
     Appleton
    0.70
    appid
    0.69
     lives
    0.69
    playerId
    0.68
     pebb
    0.68
     Gett
    0.68
    POSITIVE LOGITS
    ------------
    1.48
    ------
    1.46
    ----------------
    1.38
    -------------
    1.37
    ---------
    1.36
    --------
    1.35
    ----------
    1.34
    -----
    1.31
    ---------------
    1.28
    ----
    1.26
    Activations Density 0.481%

    No Known Activations