© 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-16K
    7. 12799
    Prev
    Next
    INDEX
    Explanations

    spoken Sanskrit

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

    speak Portuguese

    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_16k_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
    اب
    0.67
    us
    0.65
    el
    0.59
    p
    0.58
    ف
    0.57
    AI
    0.57
    ays
    0.57
    a
    0.56
    со
    0.56
    å
    0.55
    POSITIVE LOGITS
     স্প
    0.95
     स्प
    0.78
    Sp
    0.76
     sp
    0.75
     spn
    0.75
     સ્પ
    0.75
     Sp
    0.72
     ஸ்ப
    0.70
     SP
    0.69
     СП
    0.68
    Activations Density 0.349%

    No Known Activations