© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 64441
    Prev
    Next
    INDEX
    Explanations

    default connection or prediction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ك
    0.56
     Geheim
    0.50
     corresponded
    0.48
    مة
    0.47
     wissen
    0.46
    𝐠
    0.46
     Dokl
    0.45
     Kanal
    0.45
    فا
    0.44
     tatsächlich
    0.44
    POSITIVE LOGITS
     سامنا
    0.45
     ч
    0.41
    idunt
    0.41
    ведена
    0.40
     편리
    0.40
    한다
    0.39
     задача
    0.39
     한다
    0.39
     پہا
    0.39
     כש
    0.38
    Activations Density 0.002%

    No Known Activations