© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 7370
    Prev
    Next
    INDEX
    Explanations

    think about or step

    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
     don
    2.12
    נות
    2.09
    तीय
    2.05
    i
    1.95
     .”
    1.90
    preconnect
    1.90
    acqua
    1.88
     barking
    1.85
    quote
    1.85
    खिल
    1.82
    POSITIVE LOGITS
     puna
    2.60
    leri
    2.46
     nvp
    2.43
     \\\
    2.43
    鎴
    2.43
    lerinin
    2.38
    mmss
    2.37
    '\
    2.37
     $(\
    2.36
    lerini
    2.34
    Activations Density 0.144%

    No Known Activations