© 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. 22-GEMMASCOPE-2-RES-16K
    7. 8410
    Prev
    Next
    INDEX
    Explanations

    connected to systems

    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
    spur
    1.01
    CCA
    0.97
    CLI
    0.93
    attu
    0.92
    SCPC
    0.91
    감
    0.91
    opub
    0.90
    <0x8E>
    0.90
    arcie
    0.89
     newItem
    0.88
    POSITIVE LOGITS
     WOOD
    1.12
     audacious
    1.05
     risky
    1.00
     lad
    0.99
     aligned
    0.97
     audible
    0.96
    bounded
    0.95
     ALEXANDER
    0.94
     uttering
    0.94
     STONE
    0.94
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.