© 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-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 12021
    Prev
    Next
    INDEX
    Explanations

    discussion groups and lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_17_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    nhof
    0.84
     hyperbolic
    0.83
     earliest
    0.82
     rerun
    0.81
     erroneous
    0.81
     হোট
    0.80
    promise
    0.79
    செய்ய
    0.77
    擇
    0.77
     एटीएम
    0.77
    POSITIVE LOGITS
     Είναι
    1.10
     forums
    1.04
     opiniones
    0.99
     Люди
    0.98
     adhé
    0.96
     internacionais
    0.96
    যারা
    0.96
    Political
    0.94
     participatory
    0.94
     ardent
    0.94
    Activations Density 0.001%

    No Known Activations