© 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. 9202
    Prev
    Next
    INDEX
    Explanations

    concepts and conditions

    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
    <unused2117>
    0.57
     এছাড়া
    0.55
    很多
    0.51
    <unused2126>
    0.51
    ɳ
    0.50
     different
    0.50
     সাধারণভাবে
    0.50
     பொதுவாக
    0.49
    <0x11>
    0.49
    Ꮮ
    0.49
    POSITIVE LOGITS
     столь
    0.75
    简直
    0.65
     deliciously
    0.63
     великолеп
    0.61
     coveted
    0.61
     jamás
    0.61
     hapless
    0.60
     ибо
    0.57
     painstakingly
    0.57
     breathtaking
    0.57
    Activations Density 0.094%

    No Known Activations