© 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. 44351
    Prev
    Next
    INDEX
    Explanations

    whether choice

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

    notifications and asterisks

    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
     ಬಳಸ
    0.46
    korzyst
    0.46
     பொதுவாக
    0.45
    forall
    0.44
     способом
    0.44
    ವಾರು
    0.44
     עבור
    0.44
    <unused89>
    0.43
     தேவை
    0.43
     ಸುಬ್ಬ
    0.43
    POSITIVE LOGITS
     dainty
    0.49
     exhilarating
    0.47
     commotion
    0.46
    键盘
    0.46
     snowflakes
    0.45
     turista
    0.44
     fluttering
    0.44
     whirl
    0.43
     spind
    0.43
     champagne
    0.42
    Activations Density 0.001%

    No Known Activations