© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 56711
    Prev
    Next
    INDEX
    Explanations

    upstream downstream

    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
    Negative Logits
    ویه
    -0.71
    🚊
    -0.71
    tope
    -0.71
    overlay
    -0.70
    Qua
    -0.70
    ainya
    -0.69
    üksek
    -0.68
    erialized
    -0.68
     čia
    -0.68
    Attributed
    -0.68
    POSITIVE LOGITS
     downstream
    5.72
     upstream
    5.72
    upstream
    4.53
     Upstream
    4.13
    Upstream
    3.89
     Down
    2.31
    down
    2.25
    Down
    2.20
     down
    2.06
     DOWN
    1.97
    Activations Density 0.120%

    No Known Activations