© 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. 248980
    Prev
    Next
    INDEX
    Explanations

    follow-up survey

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     \
    0.49
    ниципа
    0.47
    steins
    0.45
    onnen
    0.45
    \
    0.43
    wie
    0.42
    appendTo
    0.41
    ]["
    0.41
    ftan
    0.41
    畜
    0.41
    POSITIVE LOGITS
     rojos
    0.52
    ജി
    0.52
     rối
    0.50
     Smash
    0.48
     ácido
    0.48
    ्लादेश
    0.47
     fall
    0.47
    জে
    0.46
    arlos
    0.46
    এখন
    0.46
    Activations Density 0.001%

    No Known Activations