© 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. 12783
    Prev
    Next
    INDEX
    Explanations

    fame and public attention

    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
    Климат
    -0.98
     also
    -0.96
    ია
    -0.93
    đu
    -0.91
    var
    -0.91
     компози
    -0.89
     ॥
    -0.88
    ༄
    -0.88
     we
    -0.88
     thì
    -0.86
    POSITIVE LOGITS
     popularity
    1.42
     publicity
    1.41
     people
    1.37
     public
    1.34
     Acuerdo
    1.18
     celebrity
    1.17
    Recept
    1.16
     media
    1.14
     exposição
    1.11
    车子
    1.11
    Activations Density 0.040%

    No Known Activations