© 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. 94190
    Prev
    Next
    INDEX
    Explanations

    web urls for media assets

    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
    soundcloud
    -0.75
    FAMILY
    -0.70
     pelig
    -0.70
    institutions
    -0.68
     השאלה
    -0.68
    @$
    -0.67
    推特
    -0.67
     жда
    -0.67
     brauch
    -0.66
    recommendation
    -0.66
    POSITIVE LOGITS
    cdn
    1.70
     media
    1.55
    media
    1.52
    static
    1.43
     assets
    1.33
    upload
    1.23
    assets
    1.20
     static
    1.17
     cd
    1.16
    img
    1.13
    Activations Density 0.023%

    No Known Activations