© 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. 115862
    Prev
    Next
    INDEX
    Explanations

    networking and programming concepts

    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
     cham
    -0.77
    ónio
    -0.75
    Belo
    -0.72
    ዮ
    -0.72
    Boli
    -0.71
    Deny
    -0.70
    neo
    -0.69
    ロープ
    -0.69
     Poh
    -0.69
    inov
    -0.68
    POSITIVE LOGITS
     NL
    1.49
    NL
    1.43
    nl
    1.14
     nl
    1.09
    Nl
    1.05
    ntable
    0.82
     NLA
    0.81
     Newsletter
    0.74
     dumps
    0.74
    family
    0.73
    Activations Density 0.022%

    No Known Activations