© 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. 12257
    Prev
    Next
    INDEX
    Explanations

    register or tally statistics

    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
    จะเป็น
    -0.82
     encontraban
    -0.79
    avax
    -0.77
    heard
    -0.77
    haped
    -0.76
     orgull
    -0.75
    quedo
    -0.73
     Katsu
    -0.73
    nfs
    -0.72
     pungkas
    -0.72
    POSITIVE LOGITS
     recorded
    1.83
     recording
    1.80
    recording
    1.48
     registering
    1.40
    Recording
    1.36
    Recorded
    1.33
    recorded
    1.32
     registered
    1.30
     tally
    1.29
     recorder
    1.27
    Activations Density 0.050%

    No Known Activations