© 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. 46376
    Prev
    Next
    INDEX
    Explanations

    GPU and graphics

    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
    培训
    0.54
    вшейся
    0.51
    制造业
    0.48
    
    0.47
    㝢
    0.46
    ruction
    0.46
    Noeud
    0.46
     безопас
    0.45
     эсеп
    0.45
     прось
    0.45
    POSITIVE LOGITS
     the
    0.56
     outputs
    0.56
     output
    0.54
     to
    0.52
    '
    0.52
     current
    0.52
     side
    0.52
     sources
    0.52
     a
    0.51
     pressure
    0.51
    Activations Density 0.004%

    No Known Activations