© 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. 27061
    Prev
    Next
    INDEX
    Explanations

    sipping water

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

    reduction, increase, or comparison

    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
    ጷ
    0.47
     njima
    0.46
    াহত
    0.45
     dvě
    0.43
     njega
    0.43
     ফাইল
    0.42
     সিনিয়র
    0.42
     भेजना
    0.42
     نئی
    0.42
     posao
    0.42
    POSITIVE LOGITS
    (
    0.52
     sustainably
    0.50
    🥃
    0.47
    者的
    0.47
    .
    0.46
     the
    0.45
     $(\
    0.45
    ^{+}\
    0.45
    resel
    0.45
    适
    0.45
    Activations Density 0.000%

    No Known Activations