© 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. 95438
    Prev
    Next
    INDEX
    Explanations

    date of birth

    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
     now
    -1.20
     istan
    -1.14
    Calculus
    -1.10
     habrían
    -1.06
    mathrm
    -1.05
     ormai
    -1.03
     Botox
    -1.02
    reszcie
    -1.01
    再一次
    -1.01
     };
    -0.99
    POSITIVE LOGITS
     but
    1.27
    谥
    1.20
    Ekster
    1.17
    ksessa
    1.12
    BindingResult
    1.09
    棧
    1.09
    にて
    1.09
    Reak
    1.09
     leaves
    1.07
     religiously
    1.07
    Activations Density 0.003%

    No Known Activations