© 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. 239237
    Prev
    Next
    INDEX
    Explanations

    historical context and return

    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
     postérieures
    0.52
    0
    0.51
    ansı
    0.49
    ición
    0.48
    ளிர்
    0.48
    ра
    0.47
    ینده
    0.47
    ân
    0.46
    ບໍລິ
    0.46
    습니다
    0.45
    POSITIVE LOGITS
     দরকার
    0.51
     ケ
    0.48
     ワン
    0.47
    必要があります
    0.45
     لازم
    0.45
    Ut
    0.45
     telur
    0.45
     consigli
    0.44
     hoff
    0.44
    必要
    0.44
    Activations Density 0.000%

    No Known Activations