© 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. 2347
    Prev
    Next
    INDEX
    Explanations

    lack of advertisers

    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
    Daten
    0.58
    ิตร
    0.45
    ร
    0.45
    Energie
    0.45
    че
    0.45
    น
    0.45
    Бо
    0.44
    ра
    0.42
     במש
    0.42
    婄
    0.42
    POSITIVE LOGITS
     undesirable
    0.47
     unfamiliar
    0.42
     non
    0.42
     attempted
    0.42
     inability
    0.42
     voluntarily
    0.42
     purchasers
    0.42
     unlikely
    0.42
     cannot
    0.41
     முடியாது
    0.41
    Activations Density 0.078%

    No Known Activations