© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 234085
    Prev
    Next
    INDEX
    Explanations

    flowers for remembrance

    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
     nomenclature
    0.55
    注意事項
    0.47
    nomenclature
    0.45
    hive
    0.44
    /
    0.44
     teaspoon
    0.43
     restricciones
    0.42
     Memorial
    0.42
     misdemeanor
    0.42
     Thereafter
    0.41
    POSITIVE LOGITS
     เอง
    0.52
     ቀላል
    0.51
    ertid
    0.51
     ஐந்து
    0.50
     ၀
    0.50
    нім
    0.49
     חי
    0.49
    登陆
    0.48
     dovr
    0.46
    edk
    0.46
    Activations Density 0.001%

    No Known Activations