© 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. 200368
    Prev
    Next
    INDEX
    Explanations

    sports, conditions, or items

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

    <b> or <font> start

    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
     ritmo
    0.53
     yıld
    0.47
     gelungen
    0.47
    ྞ
    0.47
     yıllık
    0.46
     skoro
    0.45
    
    0.45
     görüş
    0.45
     זו
    0.45
     kullanım
    0.45
    POSITIVE LOGITS
    at
    0.56
    aft
    0.54
    c
    0.52
    as
    0.50
    oa
    0.50
    cs
    0.49
    hs
    0.49
    oz
    0.48
    uft
    0.48
    cx
    0.48
    Activations Density 0.000%

    No Known Activations