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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 2716
    Prev
    Next
    INDEX
    Explanations

    project sections

    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
     gerai
    -0.88
    ມ
    -0.81
    listair
    -0.79
     klaus
    -0.76
    produksi
    -0.75
    vaila
    -0.73
    salary
    -0.72
    vial
    -0.71
    grees
    -0.71
    čných
    -0.70
    POSITIVE LOGITS
     project
    1.89
     client
    1.59
    Project
    1.41
    CLIENT
    1.34
     Project
    1.29
    project
    1.24
     challenges
    1.22
    Client
    1.20
     description
    1.19
    PROJECT
    1.18
    Activations Density 0.021%

    No Known Activations