© 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. 56730
    Prev
    Next
    INDEX
    Explanations

    Ongoing research and next steps

    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
    доне
    0.49
     deporte
    0.48
    dzić
    0.47
    enos
    0.46
    GUNDABAD
    0.45
    жима
    0.45
    كتور
    0.45
     deactivate
    0.45
    帆
    0.45
    ين
    0.44
    POSITIVE LOGITS
    Power
    0.43
    Benef
    0.43
    skraft
    0.43
    bing
    0.43
    hip
    0.42
    Bing
    0.41
    sunny
    0.40
    l
    0.40
    ss
    0.39
    scri
    0.39
    Activations Density 0.001%

    No Known Activations