© 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. 14035
    Prev
    Next
    INDEX
    Explanations

    URLs and links

    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
    榞
    2.23
    ქვენ
    2.19
    ifiques
    2.15
    ખ્ય
    2.14
    ायक
    2.13
     "@/
    2.05
    henburg
    2.04
     डूब
    2.02
    𝐡
    2.01
     refracting
    1.99
    POSITIVE LOGITS
    a
    1.89
    an
    1.85
    ozer
    1.78
    i
    1.72
    न
    1.70
     threaten
    1.69
     корре
    1.62
    й
    1.62
    نة
    1.60
     please
    1.60
    Activations Density 0.020%

    No Known Activations