© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 27539
    Prev
    Next
    INDEX
    Explanations

    historical locations and their purposes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    位于
    0.50
    чках
    0.50
     стимули
    0.45
    ర్రీ
    0.44
    Buildings
    0.44
    Located
    0.43
    ствах
    0.42
    馇
    0.42
    河流
    0.42
    ürdig
    0.42
    POSITIVE LOGITS
     headquarters
    0.74
     repository
    0.69
     site
    0.68
     training
    0.67
     refuge
    0.66
     venue
    0.63
     destination
    0.63
     miejsce
    0.63
     residence
    0.62
     hub
    0.61
    Activations Density 0.016%

    No Known Activations