© 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. 139027
    Prev
    Next
    INDEX
    Explanations

    holiday items

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

    sulfuric acid

    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
    ’
    0.54
     पकड़
    0.44
     P
    0.44
    signals
    0.44
    UI
    0.43
     w
    0.43
     notations
    0.42
     signal
    0.42
     trä
    0.41
     blad
    0.41
    POSITIVE LOGITS
     этом
    0.57
    езде
    0.50
    તમ
    0.50
    <0x9C>
    0.50
     சிவா
    0.49
     cay
    0.48
     તમા
    0.48
    ﺸ
    0.47
     போன்றவை
    0.47
    zeczytaj
    0.47
    Activations Density 0.000%

    No Known Activations