© 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. 1632
    Prev
    Next
    INDEX
    Explanations

    Oklahoma, Ardmore, Sooners

    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
    者
    -0.78
    loped
    -0.77
     Achievements
    -0.77
    aughn
    -0.76
     ANSWER
    -0.76
    titions
    -0.75
    AMI
    -0.72
    ceder
    -0.71
    iliki
    -0.70
     ZAP
    -0.70
    POSITIVE LOGITS
     Ard
    0.88
    ishman
    0.74
     reliable
    0.73
    Ard
    0.73
    tsx
    0.69
     citoyen
    0.69
    Обо
    0.68
    findOrFail
    0.68
    spli
    0.68
    ewear
    0.67
    Activations Density 0.012%

    No Known Activations