© 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. 157765
    Prev
    Next
    INDEX
    Explanations

    multilingual text segments

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

    category and company terms

    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
    斯
    0.52
    らす
    0.51
     CST
    0.51
     seis
    0.49
     tau
    0.48
     Pompeo
    0.48
     cuatro
    0.48
     pot
    0.47
    自
    0.47
    沼
    0.47
    POSITIVE LOGITS
     ಯಾವುದೇ
    0.55
     ಕಡಿಮೆ
    0.49
     ಒಂದ
    0.49
    uits
    0.48
     సాం
    0.47
    লিশ
    0.46
     सॉ
    0.45
     основе
    0.45
    glow
    0.45
     కె
    0.45
    Activations Density 0.000%

    No Known Activations