© 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. 246181
    Prev
    Next
    INDEX
    Explanations

    instructions and requests

    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
     są
    0.48
     تجویز
    0.46
     एग्जामिनेशन
    0.46
    荅
    0.45
    ály
    0.45
     فرمایا
    0.44
     către
    0.44
    לע
    0.44
     conséquence
    0.43
     وړاندوینه
    0.43
    POSITIVE LOGITS
    fu
    0.46
     н
    0.44
    therners
    0.43
    oi
    0.43
    రి
    0.43
    िये
    0.43
     Mu
    0.42
    ము
    0.42
    ne
    0.42
     мл
    0.42
    Activations Density 0.001%

    No Known Activations