© 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. 7-GEMMASCOPE-2-RES-16K
    7. 13821
    Prev
    Next
    INDEX
    Explanations

    scroll and back

    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
     红
    2.22
    сом
    2.08
     啊
    2.05
     Цена
    2.04
    цією
    2.04
     イタリア
    1.96
     StringSet
    1.95
     quarries
    1.95
     اہ
    1.93
     聞
    1.93
    POSITIVE LOGITS
    k
    1.98
    mtable
    1.98
    motion
    1.93
    t
    1.92
    onton
    1.89
    ."),
    1.87
    j
    1.85
    ...");
    1.84
    DOCTYPE
    1.77
    tra
    1.77
    Activations Density 0.082%

    No Known Activations