© 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. 44892
    Prev
    Next
    INDEX
    Explanations

    URLs and citations

    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
    nements
    0.42
     ентите
    0.39
    illons
    0.38
     समास
    0.38
    тента
    0.38
    ೃತ
    0.38
     endomet
    0.38
    웜
    0.38
     ამ
    0.37
     parturient
    0.37
    POSITIVE LOGITS
     atrib
    0.43
     ACID
    0.42
     a
    0.41
     kasih
    0.40
     Aplic
    0.40
    Й
    0.40
     what
    0.39
    発見
    0.39
    大きい
    0.39
     ilus
    0.39
    Activations Density 0.004%

    No Known Activations