© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 9756
    Prev
    Next
    INDEX
    Explanations

    foreign words and phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Bezeichnung
    0.42
     misconceptions
    0.42
     b
    0.41
     Thir
    0.41
    riss
    0.41
     misconception
    0.41
     korrekt
    0.41
     misinformation
    0.39
     outlines
    0.39
     두
    0.39
    POSITIVE LOGITS
     многи
    0.54
    и
    0.52
    ness
    0.48
    ра
    0.47
    на
    0.45
    гатьох
    0.45
    сида
    0.45
    想到
    0.44
    $_{
    0.44
     अफेयर्स
    0.44
    Activations Density 0.254%

    No Known Activations