© 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. 31747
    Prev
    Next
    INDEX
    Explanations

    other social fashion local listings

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

    various lottery listings and news

    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
     »
    0.43
     없고
    0.42
     ».
    0.42
     กําลัง
    0.40
    ፡
    0.40
     प्रॉब्लम
    0.40
     فقط
    0.39
     सांगतात
    0.38
    ኢ
    0.38
     ஏனெனில்
    0.37
    POSITIVE LOGITS
    ட்சய
    0.44
    ጅም
    0.42
    াবেক
    0.41
     semelh
    0.41
     પેટ્રોલ
    0.40
     연료
    0.40
     similarly
    0.39
     onshore
    0.38
    Similarly
    0.38
     longitudine
    0.38
    Activations Density 0.000%

    No Known Activations