© 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. 22-GEMMASCOPE-2-RES-16K
    7. 8289
    Prev
    Next
    INDEX
    Explanations

    presenting options, ranging

    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
    glades
    0.85
    Bur
    0.78
    bur
    0.77
    broke
    0.76
     nominated
    0.75
    λί
    0.75
     corred
    0.75
    祿
    0.74
    禄
    0.74
     categoria
    0.74
    POSITIVE LOGITS
    erm
    2.21
    ERS
    2.12
    ertype
    2.08
    erc
    2.04
    ert
    1.97
    ersk
    1.93
    erman
    1.92
    ers
    1.89
    ermark
    1.88
    ERT
    1.82
    Activations Density 0.225%

    No Known Activations