© 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. 8069
    Prev
    Next
    INDEX
    Explanations

    punctuation followed by specific letters or words

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

    mathematical equations and definitions

    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
    ylmethyl
    0.40
    기
    0.40
    캠
    0.39
     میکس
    0.38
     캠
    0.38
     اجلاس
    0.38
     کامی
    0.38
    :'],
    0.37
     وق
    0.37
     इथे
    0.37
    POSITIVE LOGITS
    Ů
    0.43
     Matemat
    0.42
     Charakter
    0.41
     первый
    0.40
    }.")
    0.40
     mă
    0.39
    做的
    0.39
     Schle
    0.39
     Heron
    0.39
     Tiro
    0.39
    Activations Density 0.000%

    No Known Activations