© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 38669
    Prev
    Next
    INDEX
    Explanations

    facebook URLs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     material
    -0.80
     quasi
    -0.79
     ὑ
    -0.74
     еди
    -0.74
     post
    -0.73
     motion
    -0.73
    贴
    -0.72
     Grundlagen
    -0.71
    回到
    -0.70
    ζ
    -0.70
    POSITIVE LOGITS
    ㄚ
    0.81
     Dadurch
    0.80
    ディダス
    0.79
    Lesen
    0.78
    newest
    0.77
    Farbe
    0.77
    šenie
    0.76
     disagree
    0.75
    oud
    0.75
    شنامهٔ
    0.75
    Activations Density 0.007%

    No Known Activations