© 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. 40-GEMMASCOPE-2-RES-65K
    7. 47646
    Prev
    Next
    INDEX
    Explanations

    jsdelivr CDN links

    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_40_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     yell
    0.39
    ☃
    0.37
    :]
    0.36
     impede
    0.36
     heed
    0.36
    olon
    0.36
    聾
    0.35
     piled
    0.35
    Ster
    0.35
     impro
    0.35
    POSITIVE LOGITS
     Finch
    0.38
    framework
    0.38
    hältnis
    0.37
    ushal
    0.37
    ्युनिटी
    0.37
    ચ્છ
    0.36
    retrato
    0.36
     Mapping
    0.36
     इच्छुक
    0.36
    芩
    0.36
    Activations Density 0.001%

    No Known Activations