© 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
    2. Gemma-3-1B
    3. 22-GEMMASCOPE-2-RES-16K
    4. 7656
    Prev
    Next
    INDEX
    Explanations

    learning_rate or similar parameters

    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
    );
    1.00
    )+
    0.99
    )+\
    0.99
    erte
    0.92
    )*
    0.91
    .);
    0.91
    )‏
    0.90
    )>
    0.88
    놉
    0.88
    보다는
    0.85
    POSITIVE LOGITS
     Zan
    1.06
     Pun
    1.05
     Mug
    0.99
     Pou
    0.99
     Poch
    0.99
     cual
    0.97
    Luna
    0.95
    Stan
    0.94
     pavimento
    0.94
     Dalton
    0.93
    Activations Density 0.001%

    No Known Activations