© 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. 180692
    Prev
    Next
    INDEX
    Explanations

    standard descriptions or rankings

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

    initial setup

    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
     Van
    0.46
     Carpathians
    0.46
     率
    0.46
     huynh
    0.45
     স্বাদ
    0.45
    -
    0.43
     <
    0.43
     おい
    0.43
     hike
    0.43
     ふ
    0.42
    POSITIVE LOGITS
    fdata
    0.62
    دد
    0.49
    йдёт
    0.47
     cardiaque
    0.46
     такая
    0.46
    Calculating
    0.45
    Пла
    0.45
     необы
    0.45
    cett
    0.45
    र्चा
    0.44
    Activations Density 0.000%

    No Known Activations