© 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. 28245
    Prev
    Next
    INDEX
    Explanations

    professions and nationalities

    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
     exhib
    -1.20
     effectuer
    -1.20
    桕
    -1.20
    ᾶ
    -1.19
     continuer
    -1.18
    -1.18
    }}.
    -1.17
     kilometer
    -1.17
    ፤
    -1.17
     كوم
    -1.16
    POSITIVE LOGITS
     in
    1.55
     (
    1.29
     just
    1.24
     after
    1.23
     chré
    1.15
     even
    1.13
     so
    1.10
     detergente
    1.10
     листья
    1.10
    ぜひ
    1.09
    Activations Density 0.047%

    No Known Activations