© 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. 34-GEMMASCOPE-RES-131K
    7. 84762
    Prev
    Next
    INDEX
    Explanations

    offers and access

    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_34/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
     offerings
    -1.06
     Angebote
    -0.97
    免費
    -0.97
     lately
    -0.90
     recently
    -0.84
     Free
    -0.84
    折叠
    -0.83
    τικός
    -0.83
    جير
    -0.83
    ὺς
    -0.82
    POSITIVE LOGITS
     lifetime
    1.26
     access
    1.20
     bonus
    1.16
     поддержку
    1.16
     workbook
    1.13
     downloadable
    1.13
     exclusive
    1.12
     your
    1.05
     support
    1.02
    PLUS
    1.01
    Activations Density 0.024%

    No Known Activations