© 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. 60431
    Prev
    Next
    INDEX
    Explanations

    cpu registers and instructions

    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
     Kemp
    -0.73
     Sot
    -0.71
    ampilkan
    -0.71
    ènements
    -0.70
    żeń
    -0.70
    IPv
    -0.70
    URAL
    -0.70
     ragazzi
    -0.69
    amb
    -0.68
    愛情
    -0.68
    POSITIVE LOGITS
     TSC
    1.08
    TSC
    0.99
    intercept
    0.91
     Melbourne
    0.85
     melk
    0.80
     intercept
    0.79
     rd
    0.76
    Lah
    0.73
    shadow
    0.73
    tsc
    0.73
    Activations Density 0.069%

    No Known Activations