Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 9071
    Prev
    Next
    INDEX
    Explanations

    unless required by applicable law or agreed to

    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
    小心
    -0.77
     Diffraction
    -0.77
     suggests
    -0.74
    bleau
    -0.71
     धन
    -0.71
    theilung
    -0.71
     SUNY
    -0.70
     Closes
    -0.70
    icum
    -0.69
     Merger
    -0.69
    POSITIVE LOGITS
     Eilish
    1.15
     Billie
    1.01
     Happ
    0.91
    Billie
    0.91
     Stratford
    0.88
     bred
    0.78
     Anaheim
    0.72
     Neighborhood
    0.71
     Grammy
    0.71
    дати
    0.70
    Activations Density 0.010%

    No Known Activations