© 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. 244130
    Prev
    Next
    INDEX
    Explanations

    language and meaning concepts

    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
    нё
    0.50
     underlie
    0.42
    apek
    0.41
    inspired
    0.41
    nyder
    0.41
     harvests
    0.41
    я
    0.41
    addWidget
    0.40
     Klein
    0.40
     أفضل
    0.40
    POSITIVE LOGITS
    Что
    0.52
    Зна
    0.51
     berakhir
    0.46
    స్
    0.46
    内地
    0.45
    肄
    0.45
    Cómo
    0.44
    Ру
    0.44
     Federación
    0.44
    Ма
    0.43
    Activations Density 0.000%

    No Known Activations