© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 212161
    Prev
    Next
    INDEX
    Explanations

    Holdings and Discovery

    np_acts-logits-general · gemini-2.5-flash-lite

    fully exited, article, 2), than gout

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     déprim
    0.59
    ≃
    0.54
     fija
    0.53
    getProgress
    0.53
     substrings
    0.52
     travailleurs
    0.52
    ⚤
    0.52
     représent
    0.50
    𝐣
    0.50
    getNum
    0.49
    POSITIVE LOGITS
     Dwarf
    0.46
    äck
    0.46
     Battery
    0.45
    olo
    0.44
     Utilizing
    0.43
     Activated
    0.41
     Connell
    0.41
     Additionally
    0.40
     Safety
    0.40
    操控
    0.40
    Activations Density 0.001%

    No Known Activations