© 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. 79608
    Prev
    Next
    INDEX
    Explanations

    company. Ads

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

    problematic concepts

    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
    騙
    0.48
    ख्या
    0.44
    骗
    0.44
    тивную
    0.43
     पक
    0.42
    鹄
    0.42
    肚子
    0.42
    स्फी
    0.41
    anjana
    0.41
     Ukraine
    0.41
    POSITIVE LOGITS
    រួម
    0.50
    Ut
    0.45
    前后
    0.43
    Lin
    0.43
     frère
    0.42
    ْ
    0.42
     dienst
    0.42
    ൻ
    0.41
     dene
    0.41
    流域
    0.41
    Activations Density 0.000%

    No Known Activations