© 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. 251917
    Prev
    Next
    INDEX
    Explanations

    positive attributes or statuses

    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
    连
    0.55
     Medford
    0.52
     两
    0.51
     Coach
    0.47
     फिसल
    0.47
     वनडे
    0.46
    跟踪
    0.45
    覆盖
    0.45
     दशहरा
    0.44
     refocus
    0.44
    POSITIVE LOGITS
     pariy
    0.50
     burdensome
    0.45
     moiety
    0.45
    )])
    0.44
     bulky
    0.43
     neoplas
    0.43
     Naira
    0.42
     epig
    0.42
     conjugation
    0.41
    ეგის
    0.41
    Activations Density 0.000%

    No Known Activations