© 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. 96608
    Prev
    Next
    INDEX
    Explanations

    do with, stewardship, combine with

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

    YAML manifests, germ layers, electronic warfare, what causes

    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
    ist
    0.55
    istance
    0.53
    moins
    0.49
    appell
    0.49
    ield
    0.48
    irne
    0.47
     :
    0.46
    main
    0.45
    orf
    0.44
    time
    0.44
    POSITIVE LOGITS
    婄
    0.49
    猗
    0.46
    犍
    0.45
    ಲಯ
    0.44
    کن
    0.43
    Ⲉ
    0.43
    튿
    0.43
     tuberc
    0.42
    Critics
    0.42
     montón
    0.42
    Activations Density 0.001%

    No Known Activations