© 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. 176483
    Prev
    Next
    INDEX
    Explanations

    describing actions or states

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

    day and greetings

    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
    大
    0.49
    О
    0.46
    edel
    0.46
    armen
    0.45
    proble
    0.45
    alle
    0.43
    efeller
    0.43
    С
    0.42
    タイル
    0.41
    성은
    0.40
    POSITIVE LOGITS
    များနှင့်
    0.48
     斜
    0.47
    သွယ်
    0.46
     દ્વારા
    0.44
    幇
    0.43
    运
    0.43
    цима
    0.43
     দ্বারা
    0.43
     Tiếp
    0.42
     الكهربائيه
    0.42
    Activations Density 0.000%

    No Known Activations