© 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. 124701
    Prev
    Next
    INDEX
    Explanations

    recommend formal statement

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

    definitions or specific terms

    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
    дование
    0.47
    В
    0.46
    p
    0.43
    solution
    0.43
    R
    0.43
    DA
    0.42
    Σ
    0.42
     precedence
    0.41
    "{
    0.41
    principal
    0.41
    POSITIVE LOGITS
     límite
    0.47
     sağlık
    0.46
     موقع
    0.45
     خیلی
    0.44
     صفح
    0.44
     πολύ
    0.43
     മണ്ണി
    0.43
     فقط
    0.43
     مستوى
    0.43
     δεί
    0.43
    Activations Density 0.003%

    No Known Activations