© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 76584
    Prev
    Next
    INDEX
    Explanations

    spectral peaks and assignments

    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
    aktionen
    -0.89
    ]._
    -0.89
     прожи
    -0.81
    omores
    -0.80
    sunny
    -0.80
    nson
    -0.77
    anii
    -0.75
    herstellung
    -0.75
     mattina
    -0.75
     descubre
    -0.74
    POSITIVE LOGITS
    shifted
    1.21
     assignments
    1.16
     assignable
    1.14
     shifted
    1.12
     assignment
    1.11
     assigned
    1.10
     sharpened
    1.09
     intensity
    1.09
     Assignments
    1.09
     shoulders
    1.06
    Activations Density 0.055%

    No Known Activations