© 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. 9120
    Prev
    Next
    INDEX
    Explanations

    Allah, entrances, when, during, ophy

    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
     صلاحیت
    0.45
     ASSEMBLY
    0.44
     certifications
    0.44
     દરેક
    0.44
     ہر
    0.44
    IQUE
    0.44
     отвечает
    0.43
     BRIDGE
    0.43
    FindingsResponse
    0.43
    ҉
    0.43
    POSITIVE LOGITS
    treat
    0.51
    tit
    0.50
    protect
    0.47
    config
    0.45
    title
    0.45
    tv
    0.41
    there
    0.41
    admin
    0.41
    heat
    0.41
    tie
    0.40
    Activations Density 0.001%

    No Known Activations