© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 25771
    Prev
    Next
    INDEX
    Explanations

    form, metaphor, fallacy, devices

    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
    ּוֹ
    -2.31
    ֶּ
    -1.73
     detalló
    -1.68
    ַּ
    -1.66
    ִּ
    -1.54
     überweisen
    -1.53
     indicó
    -1.52
     épaules
    -1.47
    ֵּ
    -1.42
     препара
    -1.37
    POSITIVE LOGITS
     повече
    1.50
     katholischen
    1.48
     usados
    1.47
     cristianismo
    1.41
     decorativos
    1.41
     chré
    1.41
     растений
    1.41
     criaturas
    1.40
     chrétien
    1.40
     тър
    1.34
    Activations Density 0.173%

    No Known Activations