© 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. 145502
    Prev
    Next
    INDEX
    Explanations

    commentator columnist comedian

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

    ok, okay, alright, shop, day

    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
     Europese
    0.46
    我已经
    0.46
     européens
    0.46
    单一
    0.46
    鞑
    0.45
    මණ
    0.43
     ጣ
    0.43
    νε
    0.42
     мин
    0.42
    сна
    0.41
    POSITIVE LOGITS
     commentator
    0.54
     می‌تواند
    0.47
    ที่จะ
    0.47
     Friend
    0.44
     Swain
    0.44
     Atkinson
    0.43
     felicit
    0.43
     coinvol
    0.43
     જોઈએ
    0.42
     columnist
    0.42
    Activations Density 0.002%

    No Known Activations