© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 116153
    Prev
    Next
    INDEX
    Explanations

    welcome you to interact

    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
    grandchildren
    -0.85
     зданий
    -0.82
    SOCK
    -0.79
    想过
    -0.75
     people
    -0.73
    дела
    -0.72
    🦢
    -0.72
    かなり
    -0.71
     unlikely
    -0.71
    别人
    -0.71
    POSITIVE LOGITS
    ^*)
    0.96
     patronage
    0.92
     cooperation
    0.90
    Yoda
    0.87
     donnera
    0.82
    能够
    0.82
    支持
    0.79
    뢰
    0.79
    能
    0.77
     escolher
    0.76
    Activations Density 0.019%

    No Known Activations