© 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-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 55460
    Prev
    Next
    INDEX
    Explanations

    patterns using words like 'or'

    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
    ociaż
    0.54
     inférieures
    0.54
    RationalValue
    0.54
     антен
    0.51
     obiettivo
    0.50
     обви
    0.49
    龴
    0.49
    これで
    0.48
    茼
    0.48
     измере
    0.48
    POSITIVE LOGITS
     or
    0.56
     council
    0.52
     GO
    0.49
     go
    0.48
     .
    0.47
     board
    0.47
     sort
    0.47
     panel
    0.47
     MD
    0.47
     premier
    0.46
    Activations Density 0.006%

    No Known Activations