© 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. 240276
    Prev
    Next
    INDEX
    Explanations

    chemical compounds and statistics

    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
    an
    0.58
     बाप
    0.55
    ರುಗ
    0.52
    fd
    0.51
     Tosh
    0.51
    ुल
    0.50
     पिताजी
    0.50
    暠
    0.47
    ifiez
    0.47
     leider
    0.47
    POSITIVE LOGITS
    وْ
    0.50
     privacy
    0.50
     refractory
    0.47
     messages
    0.43
     potassium
    0.40
     Privacy
    0.39
     symbolName
    0.39
    鉀
    0.39
     measuring
    0.38
     ব্রিগে
    0.38
    Activations Density 0.000%

    No Known Activations