© 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. 93821
    Prev
    Next
    INDEX
    Explanations

    content descriptions

    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
     Questa
    -0.84
     infest
    -0.79
     willows
    -0.77
     croissants
    -0.77
     весело
    -0.74
    Questa
    -0.71
     roti
    -0.71
    arlos
    -0.71
    niť
    -0.71
     Doom
    -0.70
    POSITIVE LOGITS
     Sandler
    1.48
     Adam
    1.10
     Happy
    1.05
     comedies
    0.83
     Spade
    0.81
    ADAM
    0.81
    Adam
    0.79
    sandy
    0.79
    Concord
    0.77
    Happy
    0.74
    Activations Density 0.013%

    No Known Activations