© 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. 238382
    Prev
    Next
    INDEX
    Explanations

    accommodation in or with

    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
     firewall
    0.48
     ආරක්ෂ
    0.45
     innumerable
    0.45
     Navarre
    0.44
     countless
    0.43
     sanction
    0.43
     Militia
    0.43
    砳
    0.43
    government
    0.43
     justices
    0.42
    POSITIVE LOGITS
    7
    0.52
    
    0.52
     家
    0.50
    4
    0.50
     カード
    0.48
    +
    0.48
    當地
    0.48
    ер
    0.47
    類型
    0.46
    Ш
    0.46
    Activations Density 0.001%

    No Known Activations