© 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. 61056
    Prev
    Next
    INDEX
    Explanations

    about instructions and explanations

    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
     Онлайн
    0.49
    Powerful
    0.48
    無
    0.47
     wobei
    0.46
    无
    0.45
     indígen
    0.44
     अरुणा
    0.44
    琤
    0.44
    సర
    0.44
    ния
    0.43
    POSITIVE LOGITS
    အ
    0.45
    factorial
    0.43
     interloc
    0.42
     hurdles
    0.41
    un
    0.40
     qualific
    0.40
    بری
    0.39
    มะ
    0.39
    钵
    0.39
    ldap
    0.39
    Activations Density 0.003%

    No Known Activations