© 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. 138957
    Prev
    Next
    INDEX
    Explanations

    FILES CON go automatically

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

    spoken words

    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
    弓
    0.45
     கும்ப
    0.43
     કેરી
    0.42
    이란
    0.41
    Calend
    0.41
    ஜ்மஹ
    0.41
     딸
    0.40
     диагностики
    0.40
    Хар
    0.40
    Д
    0.40
    POSITIVE LOGITS
     spoken
    0.52
    spoken
    0.50
     contraire
    0.50
     oldest
    0.45
     nowego
    0.45
     incroyable
    0.45
     between
    0.44
    ulai
    0.44
     Rouse
    0.44
     ciek
    0.44
    Activations Density 0.002%

    No Known Activations