© 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. 106995
    Prev
    Next
    INDEX
    Explanations

    end of sentence or phrase punctuation

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

    important disclaimer at the end

    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
    یں۔
    0.41
    ↵
    0.41
    ↵↵
    0.40
    াদিত
    0.40
    ቝ
    0.40
    SOFTWARE
    0.39
    ↵↵↵↵
    0.39
    ୃ
    0.38
    ↵↵↵
    0.38
    ্লি
    0.38
    POSITIVE LOGITS
     […]
    0.73
     
    0.67
     nbsp
    0.57
    […]
    0.57
     [...]
    0.55
     
    0.55
     
    0.52
     阅读全文
    0.52
     â
    0.51
     
    0.49
    Activations Density 0.674%

    No Known Activations