© 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. 249553
    Prev
    Next
    INDEX
    Explanations

    commercial transactions or justifications

    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
    ভুক্ত
    0.54
    ى
    0.54
    idot
    0.53
    酆
    0.51
     informação
    0.50
    ي
    0.48
     cifra
    0.48
    ի
    0.48
    ची
    0.47
    oclaw
    0.47
    POSITIVE LOGITS
     여
    0.47
    lier
    0.46
    มากขึ้น
    0.46
     좀
    0.46
     경쟁
    0.45
    横
    0.45
    緊急
    0.45
     어느
    0.45
    AV
    0.43
     누
    0.43
    Activations Density 0.000%

    No Known Activations