© 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. 73811
    Prev
    Next
    INDEX
    Explanations

    model modelPapers, tracking, ferries, chin, bonus, replica

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

    worth avoiding, saves

    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
    would
    0.52
    ْنَ
    0.52
    ی
    0.47
     would
    0.46
     څرنګوالی
    0.46
     waren
    0.46
     زیرمه
    0.45
    ہنی
    0.45
    𝑦
    0.45
     debía
    0.44
    POSITIVE LOGITS
     профессор
    0.50
     далее
    0.49
     JsonSerializer
    0.48
     Pedagog
    0.48
     администра
    0.46
     большинство
    0.46
     законода
    0.46
     Zuckerberg
    0.45
     SCIENCE
    0.45
     কূটনীতিক
    0.44
    Activations Density 0.002%

    No Known Activations