© 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. 113677
    Prev
    Next
    INDEX
    Explanations

    egg-shells to walk on

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

    adaptability and gradual change

    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
    ვენ
    0.43
     OECD
    0.41
     يعطيكم
    0.41
     وزارت
    0.40
     Cou
    0.40
    ;
    0.40
     sahib
    0.39
     availability
    0.39
     ሁለት
    0.39
     কিছুই
    0.38
    POSITIVE LOGITS
    柽
    0.50
    Potato
    0.50
    চ্ছিলাম
    0.50
     खतर
    0.49
     प्रॉब्ल
    0.49
     pitiful
    0.47
    工房
    0.46
    Hil
    0.45
    关于
    0.45
     главы
    0.45
    Activations Density 0.000%

    No Known Activations