© 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. 567
    Prev
    Next
    INDEX
    Explanations

    code print statements

    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
    <unused1949>
    1.74
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    1.71
     dilwale
    1.64
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    1.62
    <unused1959>
    1.62
    ↵↵↵↵↵↵↵↵↵↵↵↵
    1.61
     ‎
    1.60
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    1.59
     ′
    1.59
     ´
    1.57
    POSITIVE LOGITS
    Т
    1.61
    B
    1.58
    L
    1.49
    T
    1.48
    K
    1.46
    G
    1.44
    O
    1.43
    R
    1.42
    V
    1.40
    N
    1.40
    Activations Density 0.388%

    No Known Activations