© 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. 50331
    Prev
    Next
    INDEX
    Explanations

    Q&A, MFA programs, rankings

    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
     recoverable
    -0.81
    늠
    -0.78
     boxers
    -0.77
    Scénario
    -0.74
    vimeo
    -0.74
     retriever
    -0.73
    atecas
    -0.73
    cenza
    -0.73
     presumably
    -0.73
    ција
    -0.70
    POSITIVE LOGITS
     Princeton
    0.90
    again
    0.84
     student
    0.82
     STUDENT
    0.79
     praktis
    0.77
     исклю
    0.76
     value
    0.76
    <0xC8>
    0.74
     AGAIN
    0.73
     Horace
    0.73
    Activations Density 0.010%

    No Known Activations