© 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. 78438
    Prev
    Next
    INDEX
    Explanations

    date and time references

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

    analyzing, classifying, predicting

    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
    ili
    0.54
     μα
    0.50
    '
    0.49
     mart
    0.48
     iss
    0.44
    ,
    0.44
    mart
    0.43
     ho
    0.43
    ´
    0.43
     toer
    0.43
    POSITIVE LOGITS
    ЭС
    0.53
    સ્તુ
    0.49
    дини
    0.48
    దల
    0.48
     Среди
    0.47
     काशी
    0.46
    ப்பட்டு
    0.45
    ضافة
    0.45
    ள்ளது
    0.45
    总统
    0.45
    Activations Density 0.000%

    No Known Activations