© 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. 46783
    Prev
    Next
    INDEX
    Explanations

    descriptive qualities of subjects

    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
     evidencias
    0.45
    ப்புகள்
    0.43
    твы
    0.41
     reviews
    0.40
     የሆነ
    0.39
    τικής
    0.39
    തമായ
    0.39
     {-
    0.38
     ہوئے
    0.38
     বৌদ্ধ
    0.38
    POSITIVE LOGITS
     affair
    0.67
     thing
    0.54
     ஒன்றாகும்
    0.52
     Affair
    0.52
     ஒன்றாக
    0.50
    entity
    0.47
     phenomenon
    0.46
    source
    0.46
     инструмент
    0.46
     entity
    0.44
    Activations Density 0.162%

    No Known Activations