© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 87
    Prev
    Next
    INDEX
    Explanations

    operating system and software installation

    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_22_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
    ogluc
    0.99
    猗
    0.98
     Ahl
    0.95
     toplum
    0.92
    bathing
    0.91
    捋
    0.88
     inelastic
    0.87
    logits
    0.86
    _{(
    0.86
     Jahan
    0.86
    POSITIVE LOGITS
     Windows
    2.42
    Windows
    2.06
     windows
    1.95
     uninstall
    1.92
     MacOS
    1.90
     reinstall
    1.89
     installer
    1.88
     BIOS
    1.87
     Linux
    1.83
     linux
    1.82
    Activations Density 6.255%

    No Known Activations