© 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. 67652
    Prev
    Next
    INDEX
    Explanations

    achieve this

    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
     llorar
    -1.50
     encender
    -1.49
     reproducir
    -1.38
     cristianismo
    -1.32
    mschrijving
    -1.26
     mezclar
    -1.26
     trám
    -1.24
    พาะ
    -1.24
     "");
    -1.23
    鴣
    -1.23
    POSITIVE LOGITS
     this
    6.50
     these
    4.63
     that
    3.58
     этого
    3.23
     این
    2.84
     этом
    2.84
     tersebut
    2.83
     such
    2.83
    この
    2.70
     này
    2.67
    Activations Density 0.239%

    No Known Activations