© 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. 106047
    Prev
    Next
    INDEX
    Explanations

    properly dispose / incremental backup / Mix Basket / Rey Airport

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

    specific audience or context

    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
    灾
    0.55
    oree
    0.53
    ო
    0.52
     trúc
    0.49
     Americans
    0.49
     मुश्किलें
    0.49
    P
    0.48
     проекты
    0.46
    H
    0.46
    '}
    0.46
    POSITIVE LOGITS
     الصف
    0.50
    presso
    0.47
    ktiv
    0.46
    ാത്ത
    0.45
    ก็ตาม
    0.44
    für
    0.44
     зо
    0.43
    че
    0.43
    zó
    0.42
    NgramModel
    0.42
    Activations Density 0.000%

    No Known Activations