© 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. 107410
    Prev
    Next
    INDEX
    Explanations

    registration, orders, starting, text

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

    changes and improvements

    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
    ه
    0.55
    め
    0.51
    a
    0.46
     was
    0.46
    Dennis
    0.44
    صه
    0.44
     had
    0.44
    ئيه
    0.44
    初代
    0.44
    候
    0.43
    POSITIVE LOGITS
     проверка
    0.53
     शुभारंभ
    0.50
     लीजिए
    0.49
     ใ
    0.47
     ระ
    0.47
     Einsch
    0.47
     Προ
    0.46
     रहेगी
    0.46
     Ін
    0.46
     आएगी
    0.46
    Activations Density 0.002%

    No Known Activations