© 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-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 56572
    Prev
    Next
    INDEX
    Explanations

    AI servers and infrastructure

    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
    Negative Logits
     справа
    0.48
    SUV
    0.46
     αυτό
    0.44
     আহ্ব
    0.43
    </b>
    0.43
     правой
    0.43
    ABS
    0.43
     πάν
    0.42
     جسم
    0.42
     trägt
    0.42
    POSITIVE LOGITS
    o
    0.44
     Estas
    0.43
    læ
    0.43
    ujeme
    0.43
    celer
    0.41
     mocker
    0.40
    ቻ
    0.39
    éra
    0.38
     combinations
    0.38
     profiter
    0.38
    Activations Density 0.007%

    No Known Activations