© 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. 60067
    Prev
    Next
    INDEX
    Explanations

    preposition phrases

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

    scheduling and timing constraints

    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
     புல
    0.52
     slučaj
    0.46
     ദ
    0.46
    我现在
    0.45
     svijet
    0.44
     معلومات
    0.43
     видим
    0.43
     مسلح
    0.43
     अखबार
    0.42
     मुकदमा
    0.42
    POSITIVE LOGITS
     synced
    0.44
     HAT
    0.44
     docking
    0.44
    Constraint
    0.43
     ⭐
    0.42
    ঘা
    0.42
    👒
    0.42
     TWO
    0.41
     MALL
    0.41
    )。
    0.41
    Activations Density 0.001%

    No Known Activations