© 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. 172795
    Prev
    Next
    INDEX
    Explanations

    acquisitions, chapter, London

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

    greetings to names

    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
    ا
    0.54
    Ek
    0.51
    كي
    0.50
    ما
    0.49
    та
    0.49
     />
    0.47
    سي
    0.47
    ضا
    0.46
    можно
    0.45
    м
    0.45
    POSITIVE LOGITS
    เที่
    0.48
     도와
    0.48
    푀
    0.48
     কর্নে
    0.48
     देती
    0.46
    Շ
    0.44
     प्रश
    0.44
    用心
    0.44
    ⓓ
    0.44
     alternately
    0.43
    Activations Density 0.000%

    No Known Activations