© 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. 40930
    Prev
    Next
    INDEX
    Explanations

    modal verbs and requirements

    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
    Not in Any Lists

    No Comments

    Negative Logits
     polymorphisms
    0.49
     sealer
    0.48
     stipend
    0.46
     depletion
    0.46
     condenser
    0.46
     ။
    0.46
     stejně
    0.46
     cosi
    0.46
    讷
    0.46
     singlet
    0.45
    POSITIVE LOGITS
    g
    0.49
    c
    0.46
    も
    0.45
    b
    0.44
    jade
    0.44
     inconven
    0.43
    不容易
    0.43
     inconvenient
    0.43
    oh
    0.42
    т
    0.42
    Activations Density 0.002%

    No Known Activations