© 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. 63544
    Prev
    Next
    INDEX
    Explanations

    collective ownership

    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
     would
    0.52
     doable
    0.46
     طويلة
    0.44
     putea
    0.43
     could
    0.43
     podría
    0.43
    naeus
    0.41
    評
    0.41
     pourrait
    0.41
     (!)
    0.41
    POSITIVE LOGITS
     ẩn
    0.49
     Everyone
    0.46
     hidden
    0.45
     양
    0.42
     Sometimes
    0.41
    тости
    0.40
     छिपा
    0.40
     tř
    0.39
     Concentrations
    0.38
     तर्क
    0.38
    Activations Density 0.007%

    No Known Activations