© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 29366
    Prev
    Next
    INDEX
    Explanations

    go to a

    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
    Glo
    0.49
    Came
    0.48
    Accord
    0.47
    d
    0.46
     Haar
    0.44
     Desk
    0.43
     Moral
    0.43
    Jobs
    0.43
    o
    0.43
     Startup
    0.42
    POSITIVE LOGITS
     शॉपिंग
    0.60
     shopping
    0.58
    ading
    0.54
    لی
    0.52
     retrieves
    0.52
    lık
    0.52
    ies
    0.51
     enormously
    0.51
     hunting
    0.50
     fishing
    0.50
    Activations Density 0.047%

    No Known Activations