© 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. 47797
    Prev
    Next
    INDEX
    Explanations

    names or places followed by specific terms

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

    words starting with ly or lex

    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
    Ꮺ
    0.48
     IDENTITY
    0.46
    সই
    0.46
    ต้า
    0.45
    استشهاد
    0.44
    ہنی
    0.44
    cosis
    0.43
    贓
    0.43
    identité
    0.43
    ética
    0.42
    POSITIVE LOGITS
     Cosmos
    0.49
     Islington
    0.49
     निवास
    0.45
     Regent
    0.45
     Round
    0.45
     Chitt
    0.44
     Fark
    0.44
     Little
    0.44
     Primero
    0.44
     Elephant
    0.43
    Activations Density 0.002%

    No Known Activations