© 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-262K
    7. 74749
    Prev
    Next
    INDEX
    Explanations

    charming image

    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_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     of
    0.53
     upholding
    0.45
     undetected
    0.44
     kanilang
    0.44
     –
    0.41
     disposto
    0.41
     uphold
    0.41
     voisinage
    0.41
     dissenting
    0.40
     felf
    0.40
    POSITIVE LOGITS
     双
    0.50
     টুই
    0.47
     መጠቀም
    0.47
    力和
    0.46
    wag
    0.46
     क्वाड्र
    0.45
     वजन
    0.45
     మరియు
    0.45
    uu
    0.44
    ត្រូវការ
    0.44
    Activations Density 0.018%

    No Known Activations