© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 35805
    Prev
    Next
    INDEX
    Explanations

    radius and color assignments

    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
     leftWheel
    0.50
     usersRouter
    0.48
    ɹ
    0.45
    uzzi
    0.44
    трибу
    0.43
     Crude
    0.42
     ຊ
    0.41
     Species
    0.41
    KSprite
    0.41
     Fringe
    0.41
    POSITIVE LOGITS
     NAACP
    0.49
     racially
    0.45
     African
    0.41
    amo
    0.39
     Kenyatta
    0.38
    pretty
    0.38
    Punjab
    0.38
    般
    0.38
     Punjab
    0.37
     ασ
    0.37
    Activations Density 0.049%

    No Known Activations