© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 253329
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
     우선
    0.47
    ᄊ
    0.44
    აშ
    0.44
    زاده
    0.44
     वाले
    0.43
    वाले
    0.43
    老爷
    0.43
    城堡
    0.43
    ազ
    0.43
    ﺰ
    0.43
    POSITIVE LOGITS
    to
    0.47
     dynamic
    0.46
     skin
    0.45
     ইহাদের
    0.45
    ktor
    0.44
    skin
    0.44
     crunchy
    0.43
    xh
    0.43
    ade
    0.43
    rules
    0.42
    Activations Density 0.001%

    No Known Activations