© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 10766
    Prev
    Next
    INDEX
    Explanations

    description of a room

    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
    𝗰
    1.84
    욘
    1.75
    عه
    1.75
    ו
    1.64
    ﾞ
    1.58
     Stelle
    1.58
    뭔
    1.57
     पे
    1.57
    ۝
    1.54
    roda
    1.54
    POSITIVE LOGITS
    Developers
    1.98
    +="
    1.92
    ”—
    1.91
    ſs
    1.90
    ètres
    1.89
     divs
    1.88
     Roop
    1.87
     streamlit
    1.87
    囪
    1.86
     Brookfield
    1.86
    Activations Density 0.032%

    No Known Activations