© 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. 61734
    Prev
    Next
    INDEX
    Explanations

    at around, here is, here at, orthopaedic

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

    popular

    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
    sass
    0.52
    াইব
    0.47
    ષ્
    0.46
    Сі
    0.45
    亣
    0.45
     Ek
    0.44
    鹘
    0.44
    Asalamualaikum
    0.43
    ोने
    0.43
    ək
    0.43
    POSITIVE LOGITS
     zealous
    0.52
     밑
    0.52
     pubblic
    0.49
     stumpage
    0.48
     весьма
    0.47
     rambling
    0.44
     えっ
    0.44
     costruzione
    0.43
     topographical
    0.43
     furent
    0.43
    Activations Density 0.000%

    No Known Activations