© 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. 31-GEMMASCOPE-2-RES-65K
    7. 55624
    Prev
    Next
    INDEX
    Explanations

    smartphone, anxious, dependent

    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_31_width_65k_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
    ক
    0.50
    انون
    0.46
    রি
    0.44
     aperiam
    0.42
    E
    0.42
    alous
    0.42
     ENVIRONMENTAL
    0.41
     extraordinary
    0.41
    ộ
    0.41
     permeability
    0.41
    POSITIVE LOGITS
     Vermeer
    0.54
     Restaurants
    0.52
     Spam
    0.50
     торже
    0.49
     Mexiko
    0.48
     står
    0.48
     Versuch
    0.48
     tä
    0.47
    卻
    0.47
     然而
    0.47
    Activations Density 0.003%

    No Known Activations