© 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. 13269
    Prev
    Next
    INDEX
    Explanations

    brand names or specific entities

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

    stock markets, bench press, API Gateway

    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
     )
    0.28
     layout
    0.27
     Tablets
    0.27
     r
    0.26
     Postgraduate
    0.26
     sodium
    0.26
     handheld
    0.26
     l
    0.26
     ).
    0.26
     decorations
    0.26
    POSITIVE LOGITS
    נ
    0.41
    לי
    0.39
    Й
    0.39
    ני
    0.38
    И
    0.38
    Î
    0.36
    да
    0.35
    ту
    0.35
    리
    0.35
    РА
    0.35
    Activations Density 0.489%

    No Known Activations