© 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. 107663
    Prev
    Next
    INDEX
    Explanations

    place names and locations

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

    lists, like eco or wild

    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
     말미암
    0.52
     TE
    0.51
     촬영
    0.49
    喤
    0.48
     교
    0.47
     ง
    0.46
     مبت
    0.46
     हिंदी
    0.45
     EFL
    0.45
    TGF
    0.45
    POSITIVE LOGITS
    xk
    0.50
    Total
    0.49
    Một
    0.48
     empt
    0.48
    や
    0.48
    }$,
    0.47
     dryer
    0.47
    და
    0.47
    کو
    0.46
    だけ
    0.46
    Activations Density 0.001%

    No Known Activations