© 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. 7-GEMMASCOPE-2-RES-16K
    7. 2348
    Prev
    Next
    INDEX
    Explanations

    printing to console or browser

    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
    けん
    1.60
     よく
    1.52
    けて
    1.51
    નુ
    1.50
     рід
    1.49
     njihov
    1.44
    樫
    1.38
    ಕೊ
    1.37
     jų
    1.36
    オリジナル
    1.36
    POSITIVE LOGITS
     figures
    1.11
     (
    1.06
     voices
    1.06
    igure
    0.99
    ah
    0.98
     voice
    0.98
    ists
    0.95
    ảnh
    0.95
     viewer
    0.92
    ism
    0.92
    Activations Density 1.336%

    No Known Activations