© 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. 57648
    Prev
    Next
    INDEX
    Explanations

    © VA, sculpture

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

    cross-lingual content and symbols

    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
    지가
    0.50
    ного
    0.48
    йга
    0.48
    지는
    0.47
    चर्स
    0.46
    вшего
    0.46
    ?".
    0.45
    <0xD1>
    0.45
    ennies
    0.44
     выяс
    0.43
    POSITIVE LOGITS
     ہے
    0.48
    فوظ
    0.46
     ถึง
    0.45
     যেকোনো
    0.45
    列表中
    0.44
     neder
    0.44
     Neder
    0.44
     ത
    0.44
     observar
    0.43
     المجلس
    0.43
    Activations Density 0.000%

    No Known Activations