© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 38676
    Prev
    Next
    INDEX
    Explanations

    international news and media

    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_22/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
     pittores
    -1.22
     ekos
    -1.18
     visse
    -1.15
     specta
    -1.14
     suspic
    -1.11
     conster
    -1.09
     bensin
    -1.09
     indescri
    -1.08
    commented
    -1.08
     enthousi
    -1.07
    POSITIVE LOGITS
     include
    1.16
     or
    1.16
     with
    1.16
    apnews
    1.13
     også
    1.12
     dont
    1.11
     Also
    1.10
     gewähr
    1.10
    latimes
    1.09
    人不
    1.09
    Activations Density 0.027%

    No Known Activations