© 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. 100247
    Prev
    Next
    INDEX
    Explanations

    requested range

    np_acts-logits-general · gemini-2.5-flash-lite

    numbers and punctuation

    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
     limpiar
    0.44
    低
    0.42
    पुलिस
    0.42
     ガ
    0.41
     cortar
    0.41
     frutas
    0.40
     apartamento
    0.40
    ↵
    0.39
     aank
    0.39
    바
    0.39
    POSITIVE LOGITS
     ಇದು
    0.50
     ऑलरेडी
    0.49
     nõ
    0.47
     inclu
    0.45
     هذا
    0.45
     allerede
    0.45
     already
    0.44
     included
    0.42
     Included
    0.42
     Untersuchungen
    0.42
    Activations Density 0.001%

    No Known Activations