© 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. 33584
    Prev
    Next
    INDEX
    Explanations

    topic models and distributions

    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
    𝚕
    -0.77
     Leading
    -0.75
     fisico
    -0.74
    ᱶ
    -0.70
    spo
    -0.70
     impatiently
    -0.70
     físicos
    -0.69
    enemy
    -0.69
    รา
    -0.68
    Leading
    -0.68
    POSITIVE LOGITS
     stick
    1.08
    Concentration
    0.98
     Concentration
    0.94
    Wish
    0.91
     Stick
    0.91
     concentration
    0.91
     Beta
    0.90
    concentration
    0.90
     prior
    0.89
     Wish
    0.88
    Activations Density 0.032%

    No Known Activations