© 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. 137035
    Prev
    Next
    INDEX
    Explanations

    last month

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

    gender stereotypes, perplexity, synchronization

    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
     dept
    0.45
    奥行
    0.43
     油
    0.43
     d
    0.42
     Laugh
    0.41
     org
    0.41
    AH
    0.40
     star
    0.39
    ਪਣ
    0.39
    ടൊപ്പം
    0.39
    POSITIVE LOGITS
    २
    0.55
     месяц
    0.53
     частично
    0.51
     брать
    0.50
    ३
    0.49
     система
    0.48
    grupo
    0.48
    शरी
    0.47
    iguë
    0.46
     शिक्षक
    0.46
    Activations Density 0.000%

    No Known Activations