© 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. 2372
    Prev
    Next
    INDEX
    Explanations

    language questions

    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
    =");
    0.48
    ASSOCI
    0.47
     rearrangements
    0.46
    入り
    0.42
    planting
    0.42
    মায়
    0.41
    ভেল
    0.41
     CHANGES
    0.41
    llbracket
    0.41
    蟎
    0.40
    POSITIVE LOGITS
     Го
    0.42
     întreb
    0.42
     Campaign
    0.41
     Tel
    0.40
     предвари
    0.39
     Defin
    0.38
     Mal
    0.38
     Pare
    0.38
     Hacer
    0.38
     Miche
    0.38
    Activations Density 0.001%

    No Known Activations