© 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. 54973
    Prev
    Next
    INDEX
    Explanations

    corner shelf

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

    new foreign words

    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
    鹕
    0.50
    ंनो
    0.44
     rừng
    0.43
    zyć
    0.43
     туристов
    0.43
    कडील
    0.42
    ிலுள்ள
    0.41
    苡
    0.41
    यॉर्क
    0.41
    REGIUNE
    0.41
    POSITIVE LOGITS
     thats
    0.48
     kaip
    0.47
     Download
    0.45
     hlav
    0.44
     novas
    0.44
    žem
    0.43
     WTF
    0.43
     neue
    0.43
     novos
    0.42
    webm
    0.42
    Activations Density 0.000%

    No Known Activations