© 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. 121888
    Prev
    Next
    INDEX
    Explanations

    place names and common phrases

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

    AI-Powered Features

    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
     драматур
    0.49
    𝗢
    0.44
     дра
    0.43
     chuan
    0.43
    ทธิ
    0.43
     regrett
    0.42
     Shekhar
    0.42
    ‚
    0.42
    CHREIB
    0.42
    サプライ
    0.41
    POSITIVE LOGITS
     کارکن
    0.47
    twisted
    0.45
     CONGRESS
    0.45
    j
    0.44
     কর্মকর্তারা
    0.43
     স্টাফ
    0.42
    ری
    0.41
     interpretación
    0.41
    incible
    0.41
    برها
    0.41
    Activations Density 0.001%

    No Known Activations