© 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
    2. Gemma-3-1B
    3. 7-GEMMASCOPE-2-RES-16K
    4. 737
    Prev
    Next
    INDEX
    Explanations

    Scope

    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
    Not in Any Lists

    No Comments

    Negative Logits
    س
    1.31
    ново
    1.31
    山区
    1.26
     ге
    1.26
    captured
    1.23
    lemon
    1.22
    glob
    1.22
    orange
    1.22
    :*
    1.21
    تو
    1.21
    POSITIVE LOGITS
     wszyscy
    2.08
     fakat
    1.73
     corazón
    1.71
     haremos
    1.68
     semuanya
    1.67
     ardından
    1.66
     esso
    1.65
     sareng
    1.64
     éventuellement
    1.64
     asimismo
    1.63
    Activations Density 0.010%

    No Known Activations