© 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. 92028
    Prev
    Next
    INDEX
    Explanations

    store names/class/Id/Url

    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
    ser
    -1.02
    during
    -0.97
     spectacular
    -0.93
     فول
    -0.91
    two
    -0.90
    cribing
    -0.89
    advice
    -0.88
     darbu
    -0.88
    垟
    -0.87
    ethe
    -0.86
    POSITIVE LOGITS
    🏬
    1.31
    house
    1.05
     store
    1.01
     locator
    0.97
    ));
    0.97
    ́
    0.97
     storing
    0.96
    houses
    0.96
     Stor
    0.94
    槙
    0.93
    Activations Density 0.023%

    No Known Activations