© 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. 139669
    Prev
    Next
    INDEX
    Explanations

    preposition followed by noun

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

    step-by-step instructions and guides

    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
    T
    0.55
    量子
    0.47
    N
    0.45
    E
    0.45
     doubly
    0.44
    Servers
    0.42
    V
    0.42
    ”,
    0.40
    0.39
    S
    0.39
    POSITIVE LOGITS
     সাবধান
    0.52
    ώντας
    0.49
     జాగ్ర
    0.48
     স্টোন
    0.48
     परंपरा
    0.46
     створення
    0.45
    მართ
    0.45
     Γερμαν
    0.45
     postponement
    0.45
     любовь
    0.44
    Activations Density 0.001%

    No Known Activations