© 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. 27479
    Prev
    Next
    INDEX
    Explanations

    social media mentions and links

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

    Okay, then, here are

    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
     armchair
    0.46
    𝘈
    0.45
     moles
    0.43
     dumpster
    0.40
    ួរ
    0.40
     দক্ষতা
    0.40
    λικ
    0.40
     incorrect
    0.39
    जानकारी
    0.39
    mole
    0.39
    POSITIVE LOGITS
    ssk
    0.40
    我们的
    0.39
    泌
    0.38
    izamos
    0.36
     ნ
    0.36
    ssss
    0.36
    유
    0.36
     Hopefully
    0.35
    ipin
    0.35
     अयोध्या
    0.35
    Activations Density 0.000%

    No Known Activations