© 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. 34867
    Prev
    Next
    INDEX
    Explanations

    one-to-many relationships

    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
    ComponentModel
    -0.80
    bumptech
    -0.77
    了两
    -0.76
    ⍨
    -0.75
    SCs
    -0.75
    Thành
    -0.74
    か月
    -0.74
     février
    -0.74
     Cl
    -0.73
     какие
    -0.71
    POSITIVE LOGITS
     many
    4.97
    many
    3.81
    Many
    3.59
     Many
    3.41
    MANY
    3.20
     MANY
    3.08
     viele
    2.83
     nhiều
    2.78
     molti
    2.73
     muitos
    2.73
    Activations Density 0.065%

    No Known Activations