© 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. 98674
    Prev
    Next
    INDEX
    Explanations

    availability announcements

    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
     tetto
    -1.15
    ların
    -1.13
    /***
    -1.11
    ebly
    -1.07
    mathbb
    -1.05
     on
    -1.02
    ELTS
    -1.02
    ADT
    -1.00
    nadequate
    -0.98
     in
    -0.98
    POSITIVE LOGITS
     available
    2.86
    Available
    2.41
    available
    2.19
     Available
    1.93
     disponibles
    1.86
     disponible
    1.83
     avail
    1.70
     disponibile
    1.68
     AVAILABLE
    1.61
     purchase
    1.52
    Activations Density 0.049%

    No Known Activations