© 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. 41-GEMMASCOPE-2-RES-262K
    7. 30021
    Prev
    Next
    INDEX
    Explanations

    green positive words

    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_all/layer_41_width_262k_l0_big
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    泫
    0.39
     secondaire
    0.38
     desvent
    0.37
     disadvantage
    0.37
    octopus
    0.37
     deprive
    0.37
    纡
    0.36
    রো
    0.36
    ㄈ
    0.36
    リエステル
    0.36
    POSITIVE LOGITS
     positive
    1.46
    Positive
    1.41
    positive
    1.34
     Positive
    1.33
     positives
    1.26
     положи
    1.23
     सकारात्मक
    1.22
     positivas
    1.22
    POSITIVE
    1.22
     positif
    1.21
    Activations Density 0.005%

    No Known Activations