© 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. 161614
    Prev
    Next
    INDEX
    Explanations

    sending, foreign languages

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

    punctuation and lists

    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
     Clayton
    0.49
    ഋ
    0.48
     Lel
    0.48
     Adolf
    0.47
     Pritchard
    0.46
    ('../
    0.45
     Swanson
    0.44
     darle
    0.43
    ਈ
    0.43
     Berlusconi
    0.43
    POSITIVE LOGITS
    蠍
    0.50
     পাঠিয়ে
    0.47
     certificates
    0.47
     ارسال
    0.46
    າມາດ
    0.46
     corticoster
    0.45
    τε
    0.44
     καθ
    0.44
     보내
    0.44
    ການ
    0.43
    Activations Density 0.000%

    No Known Activations