© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 8884
    Prev
    Next
    INDEX
    Explanations

    starts of clauses or noun phrases

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

    global configuration

    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
    ารถ
    0.51
    ⴷ
    0.47
    він
    0.46
    スーツ
    0.46
    敵人
    0.43
    敵
    0.43
    ವರೆಗೆ
    0.43
     світу
    0.41
    ською
    0.41
    ഗ്രഹം
    0.41
    POSITIVE LOGITS
     If
    0.52
    c
    0.48
    ↵
    0.48
     eğer
    0.44
     chanc
    0.42
    ar
    0.42
     tipped
    0.42
     if
    0.42
     El
    0.41
     oleh
    0.41
    Activations Density 0.000%

    No Known Activations