© 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. 194018
    Prev
    Next
    INDEX
    Explanations

    numbers and foreign words

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

    intellectual and emotional belonging

    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
     a
    0.52
    یس
    0.49
     inextric
    0.47
     inventories
    0.44
     pernicious
    0.44
     Parece
    0.43
     deux
    0.43
    ્યા
    0.42
     however
    0.42
     mistakes
    0.41
    POSITIVE LOGITS
     روپے
    0.45
     అందించ
    0.44
    ዬ
    0.43
     SAME
    0.42
     હું
    0.41
    我已经
    0.41
     কাপ
    0.41
    為了
    0.40
     विप
    0.40
     SMALL
    0.40
    Activations Density 0.000%

    No Known Activations