© 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. 164314
    Prev
    Next
    INDEX
    Explanations

    for different

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

    companies or specific identifiers

    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
     Elasticsearch
    0.50
     Authent
    0.48
    新鲜
    0.47
     Notices
    0.45
     Password
    0.45
    ا
    0.44
     Synopsis
    0.44
     Absence
    0.43
    ن
    0.43
     Dan
    0.42
    POSITIVE LOGITS
    abhut
    0.54
    lestage
    0.53
    resultado
    0.51
    resultados
    0.49
    cami
    0.49
    ikas
    0.49
    pper
    0.48
    aka
    0.48
     levando
    0.47
    dept
    0.47
    Activations Density 0.000%

    No Known Activations