© 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. 25215
    Prev
    Next
    INDEX
    Explanations

    This brand, the table, produces

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

    understanding the

    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
    ol
    0.54
    m
    0.52
    vo
    0.50
    aaaa
    0.50
    aaa
    0.50
    t
    0.50
    et
    0.49
    alet
    0.49
    tags
    0.49
    võ
    0.48
    POSITIVE LOGITS
    ุ่ม
    0.46
     PAINE
    0.44
    Ы
    0.43
    циях
    0.42
    ﺔ
    0.42
    اري
    0.42
     диа
    0.42
    نتي
    0.42
    мати
    0.42
     жизнен
    0.42
    Activations Density 0.000%

    No Known Activations