© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 7077
    Prev
    Next
    INDEX
    Explanations

    introducing examples or instances

    np_acts-logits-general · gemini-2.5-flash-lite

    for example

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    म्स
    0.55
    ㇂
    0.55
    Aslamualaikum
    0.54
    ாங்க
    0.52
    রির
    0.51
    in
    0.51
    ಸ್ಕೊ
    0.51
     農
    0.50
     nemá
    0.49
    oS
    0.49
    POSITIVE LOGITS
     sake
    0.98
     purposes
    0.78
    giveness
    0.77
     starters
    0.73
    ced
    0.71
    cing
    0.66
    erunner
    0.64
     Sake
    0.63
     centuries
    0.62
     instance
    0.58
    Activations Density 0.177%

    No Known Activations