© 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. 218612
    Prev
    Next
    INDEX
    Explanations

    growth rate

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

    say that

    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
    ვ
    0.49
    ار
    0.49
    нар
    0.47
    仨
    0.45
    тан
    0.45
    ادل
    0.45
     Dolom
    0.44
    اران
    0.44
     deuteron
    0.44
    喉
    0.43
    POSITIVE LOGITS
     તેમજ
    0.50
     Поэтому
    0.50
    ounid
    0.46
    ücksicht
    0.46
    coprotein
    0.46
     단순히
    0.44
     সুতরাং
    0.43
     criticize
    0.42
     तसेच
    0.41
     تقریباً
    0.41
    Activations Density 0.002%

    No Known Activations