© 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. 195638
    Prev
    Next
    INDEX
    Explanations

    war erupting

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

    withstand significant

    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
    ليف
    0.43
    ülés
    0.43
    ئة
    0.41
    建设项目
    0.41
    囫
    0.40
    ゾーン
    0.40
    鋁
    0.40
    ــــ
    0.40
    ческая
    0.39
    ㎡
    0.39
    POSITIVE LOGITS
     tweeting
    0.47
     polarised
    0.45
     pangkat
    0.45
     polarisation
    0.44
     testifying
    0.44
    的這個
    0.44
     geopol
    0.42
     handbags
    0.42
     libertarian
    0.41
     reporting
    0.41
    Activations Density 0.001%

    No Known Activations