© 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. 179433
    Prev
    Next
    INDEX
    Explanations

    selection of people

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

    philosophical and technical concepts

    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
     fusing
    0.47
    fetching
    0.45
    ার্থীরা
    0.45
    หัส
    0.45
     continuing
    0.45
     ਵੀ
    0.44
    prochen
    0.43
    ਦ
    0.43
    áf
    0.42
    ătă
    0.42
    POSITIVE LOGITS
     mae
    0.54
     QtWidgets
    0.46
     azi
    0.46
     revolutionaries
    0.46
     anarch
    0.45
     dha
    0.45
     ma
    0.45
     avut
    0.44
     nel
    0.44
     aquela
    0.44
    Activations Density 0.000%

    No Known Activations