© 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. 115956
    Prev
    Next
    INDEX
    Explanations

    .

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

    phrases ending in punctuation or newline

    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
    క్త
    0.49
    ర్‌
    0.46
     Size
    0.45
    Size
    0.43
     Inches
    0.43
     SIZE
    0.42
    客戶
    0.42
    ฝ
    0.42
    ickej
    0.41
    綰
    0.41
    POSITIVE LOGITS
    dV
    0.49
     pharmaceut
    0.46
     threatens
    0.46
     dwarves
    0.46
     explains
    0.46
     yeni
    0.46
     dwellers
    0.45
     excreted
    0.45
     artistes
    0.44
    rasında
    0.44
    Activations Density 0.000%

    No Known Activations