© 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. 76838
    Prev
    Next
    INDEX
    Explanations

    AWS job roles and services

    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
    getCmp
    -0.77
     hablaba
    -0.75
    ecen
    -0.73
    ませんでした
    -0.73
     mây
    -0.70
     Costco
    -0.68
    Trimethyl
    -0.68
    Lma
    -0.67
     helst
    -0.67
     médaille
    -0.66
    POSITIVE LOGITS
     Presse
    0.96
    Solving
    0.85
     architectural
    0.84
     primers
    0.82
     sovereignty
    0.81
    ranje
    0.80
    čiau
    0.78
    🤿
    0.78
     ORANGE
    0.78
    badge
    0.75
    Activations Density 0.039%

    No Known Activations