© 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. 210920
    Prev
    Next
    INDEX
    Explanations

    mysteries, surname, privacy, cider

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

    jokes aboutFinancial Sectorword equatesyes

    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
    infini
    0.49
     প্রভৃতির
    0.45
    ழிவு
    0.45
    뉩
    0.45
    іга
    0.45
    ণীর
    0.45
    lingwood
    0.45
    শরণ
    0.44
    ibin
    0.43
    ipedia
    0.43
    POSITIVE LOGITS
     Fitzpatrick
    0.55
    )
    0.51
     هست
    0.47
     angenommen
    0.47
     but
    0.46
     or
    0.46
    ＞
    0.46
     Zahl
    0.45
     daftar
    0.44
     not
    0.42
    Activations Density 0.001%

    No Known Activations