© 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. 76500
    Prev
    Next
    INDEX
    Explanations

    lists common actions or states

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

    alluring, sensing, needing, good

    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
    с
    0.45
     כאשר
    0.43
    prepare
    0.43
    iaio
    0.42
     લઈને
    0.42
    マラ
    0.39
     erd
    0.39
    mér
    0.39
    initializeApp
    0.38
     बाहरी
    0.38
    POSITIVE LOGITS
    ADA
    0.59
    AKE
    0.48
    =("
    0.47
    _{(\
    0.47
     argomento
    0.46
     manifestazione
    0.46
     kated
    0.46
     চালানো
    0.46
     แม่
    0.46
     انسٹ
    0.46
    Activations Density 0.000%

    No Known Activations