© 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. 99939
    Prev
    Next
    INDEX
    Explanations

    specific nouns or actions

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

    content moderation

    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
     unsure
    0.47
    尬
    0.46
    駁
    0.46
    Pada
    0.45
     হালকা
    0.45
    Stack
    0.44
    𝐸
    0.44
    nelly
    0.44
    痧
    0.44
     Paxton
    0.43
    POSITIVE LOGITS
     masterpieces
    0.53
     THEIR
    0.50
     globals
    0.48
     훨씬
    0.47
    둡
    0.47
     enormously
    0.45
     immensely
    0.42
     продукт
    0.42
     experts
    0.41
    тего
    0.41
    Activations Density 0.001%

    No Known Activations