© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 91034
    Prev
    Next
    INDEX
    Explanations

    offer customizations, detail of, officials accept

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

    beginner language learning

    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
    Negative Logits
    𝚂
    0.52
    ｿ
    0.49
     قابلیت
    0.47
    Reusable
    0.46
    𝙎
    0.46
    <unused2049>
    0.45
     แทน
    0.45
     ያሉ
    0.45
    φέρ
    0.44
    <unused188>
    0.44
    POSITIVE LOGITS
     beginnings
    0.47
     comienzo
    0.46
     língua
    0.46
    begin
    0.46
     slightly
    0.45
     comic
    0.45
    his
    0.42
    ike
    0.41
    are
    0.41
     beginning
    0.41
    Activations Density 0.001%

    No Known Activations