© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 54074
    Prev
    Next
    INDEX
    Explanations

    non-english text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     is
    0.46
    んは
    0.43
    ೇವಿನ
    0.41
     totiž
    0.41
     was
    0.40
     $(
    0.39
     semblent
    0.37
     و
    0.36
    ERNAL
    0.36
    يرو
    0.36
    POSITIVE LOGITS
    涵盖
    0.46
    เฉพาะ
    0.46
     अपनी
    0.44
    на
    0.42
    idega
    0.41
    ק
    0.40
    ंपरिक
    0.40
    适合
    0.40
     формат
    0.40
    दायक
    0.39
    Activations Density 0.001%

    No Known Activations