© 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. 220126
    Prev
    Next
    INDEX
    Explanations

    county names

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

    cultural significance and relevance

    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
     undergraduates
    0.47
     kteří
    0.46
    РСР
    0.45
     nud
    0.45
     ONLINE
    0.44
     girly
    0.44
    जिट
    0.44
    }`}>
    0.42
     bahan
    0.42
     آنلاین
    0.42
    POSITIVE LOGITS
    7
    0.49
    ikawa
    0.46
    erved
    0.46
    8
    0.46
    iformes
    0.45
    imagen
    0.45
    ermodel
    0.44
    ño
    0.44
    ños
    0.44
     compañía
    0.44
    Activations Density 0.003%

    No Known Activations