© 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. 13036
    Prev
    Next
    INDEX
    Explanations

    authors writing and explaining

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

    authors and their writings

    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
     تبقى
    0.46
     შემ
    0.42
    க்கப்பட்டது
    0.41
     వీడియో
    0.40
    ◝
    0.40
    يبقى
    0.39
    𝓁
    0.39
     요즘
    0.38
     walkways
    0.38
    ން
    0.38
    POSITIVE LOGITS
     writes
    0.65
     लिखते
    0.63
     writing
    0.62
     escribe
    0.62
     write
    0.54
     লিখিয়াছেন
    0.54
     نویس
    0.54
     пишет
    0.52
     escrever
    0.51
     எழுது
    0.51
    Activations Density 0.090%

    No Known Activations