© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 220510
    Prev
    Next
    INDEX
    Explanations

    f-strings and Python 3.6+

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Axes
    0.39
    haben
    0.38
    ⾏
    0.38
    šću
    0.38
    Axes
    0.37
    zip
    0.37
     φο
    0.37
    isent
    0.36
    planar
    0.36
     তৈরির
    0.36
    POSITIVE LOGITS
    롬
    0.42
    לו
    0.39
    كلمنا
    0.39
    ጶ
    0.38
     neuritis
    0.37
     நாட்ட
    0.37
     levelled
    0.36
    elijkheid
    0.36
     सिल्वर
    0.36
    ایا
    0.35
    Activations Density 0.000%

    No Known Activations