© 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. 16-GEMMASCOPE-2-RES-262K
    7. 116146
    Prev
    Next
    INDEX
    Explanations

    Doctor Who, local resource, area

    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_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    Ev
    0.58
    Find
    0.54
    Crew
    0.53
    Est
    0.53
    Banks
    0.51
    Ex
    0.51
    Brid
    0.50
    S
    0.50
    E
    0.50
    Election
    0.50
    POSITIVE LOGITS
     новое
    0.60
     déprim
    0.59
    ような
    0.56
     новым
    0.55
     निर्मला
    0.55
     忄
    0.55
    рино
    0.54
     измене
    0.54
     OCPP
    0.54
     Цуки
    0.53
    Activations Density 0.001%

    No Known Activations