© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 108869
    Prev
    Next
    INDEX
    Explanations

    programming directives and 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
    viously
    -0.93
    绸
    -0.89
     urugu
    -0.84
    claro
    -0.83
    ография
    -0.83
    corns
    -0.82
    länge
    -0.81
    ]!='
    -0.81
    cartier
    -0.81
    sew
    -0.81
    POSITIVE LOGITS
     namespace
    1.23
    with
    0.93
    itzung
    0.85
     мето
    0.82
     as
    0.77
    琏
    0.77
     Partnerships
    0.76
    úly
    0.76
     using
    0.76
     pran
    0.76
    Activations Density 0.011%

    No Known Activations