© 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. 60122
    Prev
    Next
    INDEX
    Explanations

    Professional clinical supervisors

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

    earth and rocks

    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
    takes
    0.42
     プリント
    0.41
     送料無料
    0.40
    רית
    0.40
    reflectionMap
    0.39
    ד
    0.39
    edizione
    0.38
    迺
    0.38
    エントリー
    0.38
    ambahkan
    0.37
    POSITIVE LOGITS
     effectués
    0.43
     plupart
    0.40
     suốt
    0.40
     ያል
    0.39
     tất
    0.38
     Stadion
    0.38
     Gegner
    0.38
     zwycię
    0.38
     военных
    0.37
     Điện
    0.36
    Activations Density 0.000%

    No Known Activations