© 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. 117588
    Prev
    Next
    INDEX
    Explanations

    technical requirements and configurations

    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
     M
    -2.05
    ,
    -1.96
    $
    -1.92
     L
    -1.89
     S
    -1.89
     K
    -1.89
     Y
    -1.88
     J
    -1.85
     H
    -1.84
     P
    -1.80
    POSITIVE LOGITS
    ↵↵
    4.25
    ↵
    2.50
     améli
    2.00
    Noter
    1.98
    Nachteile
    1.93
     étan
    1.89
     atmósfera
    1.89
     finanzas
    1.84
    쐈
    1.83
     notwendigen
    1.82
    Activations Density 0.227%

    No Known Activations