© 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. 22-GEMMASCOPE-RES-131K
    7. 68802
    Prev
    Next
    INDEX
    Explanations

    entertainment magazines

    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
    
    -1.18
    ticky
    -1.10
    always
    -1.09
    extremely
    -1.08
    ευ
    -1.04
    ystems
    -1.04
    原材料
    -1.04
    ETIES
    -1.04
    GetField
    -1.02
    étaires
    -1.01
    POSITIVE LOGITS
     may
    1.23
     can
    1.21
     after
    1.20
     with
    1.16
     while
    1.14
     should
    1.13
     during
    1.13
     when
    1.12
    *
    1.11
    !
    1.06
    Activations Density 0.002%

    No Known Activations