© 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. 37879
    Prev
    Next
    INDEX
    Explanations

    monthly annual yearly subscriptions

    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
    лактика
    -0.82
    Semif
    -0.81
    GLfloat
    -0.80
    acebook
    -0.80
     stanu
    -0.77
     modificaciones
    -0.75
    ashion
    -0.75
    allocate
    -0.75
    tituto
    -0.74
     Bris
    -0.73
    POSITIVE LOGITS
     subscription
    5.81
     subscriptions
    5.03
    subscription
    4.56
     membership
    4.38
    Subscription
    4.38
     Subscription
    4.28
    subscriptions
    3.69
     Subscriptions
    3.67
     memberships
    3.66
    Subscriptions
    3.59
    Activations Density 0.069%

    No Known Activations