© 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. 40-GEMMASCOPE-2-RES-65K
    7. 1194
    Prev
    Next
    INDEX
    Explanations

    updates and code

    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_40_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
    3
    0.53
    2
    0.43
    4
    0.43
    are
    0.43
    .
    0.42
    7
    0.42
    ่
    0.41
     XNUMX
    0.41
    8
    0.41
    umber
    0.39
    POSITIVE LOGITS
     socalled
    0.63
     、,
    0.46
         
    0.44
          
    0.44
    꼫
    0.42
     វា
    0.40
     wellknown
    0.40
    됩
    0.40
     sosok
    0.39
     τε
    0.38
    Activations Density 0.129%

    No Known Activations