© 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. 247638
    Prev
    Next
    INDEX
    Explanations

    forthcoming report, until regulations, served as

    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
     Huyền
    0.50
    পত্র
    0.49
    子ども
    0.44
    Description
    0.43
    -
    0.43
     PVP
    0.42
    était
    0.41
     podia
    0.41
    ada
    0.41
     podía
    0.41
    POSITIVE LOGITS
     תק
    0.52
     వచ్చ
    0.50
     الاول
    0.49
    ድ
    0.49
     እንደሚ
    0.46
     Vil
    0.46
     vjer
    0.46
    ವಿಧ
    0.46
    指數
    0.45
     vil
    0.45
    Activations Density 0.000%

    No Known Activations