© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 59870
    Prev
    Next
    INDEX
    Explanations

    actions followed by out, on, up

    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
     into
    -1.22
     back
    -0.79
     all
    -0.74
     steig
    -0.73
     off
    -0.73
     onto
    -0.72
    済
    -0.67
    ๔
    -0.66
     outbreak
    -0.66
     only
    -0.66
    POSITIVE LOGITS
    (;;)
    0.92
     Produce
    0.89
    produce
    0.86
    Produce
    0.85
    Delivered
    0.84
     ajuta
    0.84
    meteries
    0.82
     produz
    0.82
     стране
    0.82
    ٤
    0.81
    Activations Density 0.018%

    No Known Activations