© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 109696
    Prev
    Next
    INDEX
    Explanations

    javascript module imports

    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
     blusa
    -1.13
     fotógrafo
    -1.12
     camada
    -1.04
     bancada
    -1.00
     malha
    -1.00
     PRESENTED
    -1.00
     moldura
    -0.99
    MERCIAL
    -0.98
     músico
    -0.98
     garrafa
    -0.98
    POSITIVE LOGITS
     fs
    1.66
     {
    1.56
     {
    1.35
    fs
    1.34
     chalk
    1.27
    {
    1.11
     crypto
    1.08
    SPATH
    1.05
     constants
    1.03
     also
    1.02
    Activations Density 0.019%

    No Known Activations