© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 70996
    Prev
    Next
    INDEX
    Explanations

    availability inquiries and ingredients

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

    flags and options

    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
    Negative Logits
    硅
    0.46
     thunder
    0.45
    氣
    0.45
    交代
    0.44
     stri
    0.43
    wink
    0.42
    id
    0.42
    ิ้ง
    0.42
    ید
    0.42
    どうしても
    0.41
    POSITIVE LOGITS
     ৩৬
    0.49
     Yardım
    0.49
    ремя
    0.48
    ậm
    0.48
    сро
    0.46
     الوزن
    0.46
    Ğ
    0.46
    ţional
    0.45
    .:
    0.45
     Renal
    0.45
    Activations Density 0.001%

    No Known Activations