© 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. 228878
    Prev
    Next
    INDEX
    Explanations

    administrator. This

    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
    gruppen
    0.52
     peralatan
    0.46
    group
    0.45
    MBOLS
    0.44
    $.}
    0.43
    pac
    0.43
    none
    0.42
    mi
    0.41
    alq
    0.41
    gather
    0.41
    POSITIVE LOGITS
     bessere
    0.50
    远的
    0.49
    远
    0.49
     schönen
    0.48
     naturelles
    0.48
     좋은
    0.48
     conséquent
    0.47
     budynku
    0.46
     bénéficier
    0.46
     supprimer
    0.45
    Activations Density 0.000%

    No Known Activations