© 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. 98630
    Prev
    Next
    INDEX
    Explanations

    currency symbols or abbreviations

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

    bamboo munching

    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
    ers
    0.45
    tså
    0.44
    default
    0.41
    ,
    0.41
    self
    0.41
    db
    0.41
    aron
    0.41
    riter
    0.41
    inkel
    0.41
    Donald
    0.40
    POSITIVE LOGITS
     実
    0.53
    <unused2018>
    0.51
    뭄
    0.50
     Dij
    0.49
     ಕೂದಲ
    0.49
    実
    0.48
     に関
    0.48
     剤
    0.47
    ថ្
    0.47
     excretion
    0.47
    Activations Density 0.000%

    No Known Activations