© 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. 84167
    Prev
    Next
    INDEX
    Explanations

    select Panini America

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

    parts of speech

    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
    leftChild
    0.53
     geï
    0.52
     vijf
    0.51
    ❿
    0.51
     jeweil
    0.50
    ستي
    0.50
    زع
    0.50
     jeweiligen
    0.49
    ٻ
    0.48
    بعد
    0.48
    POSITIVE LOGITS
    (
    0.60
    ar
    0.50
    atinum
    0.46
    n
    0.46
    oma
    0.45
    apal
    0.44
    ors
    0.44
    ates
    0.43
    activity
    0.43
    0.43
    Activations Density 0.002%

    No Known Activations