© 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. 98064
    Prev
    Next
    INDEX
    Explanations

    numbers and words followed by specific punctuation or words

    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
    теры
    -1.00
     tekst
    -0.94
     kamera
    -0.90
     karta
    -0.88
     kapital
    -0.85
     kriminal
    -0.83
    ández
    -0.82
     Itali
    -0.82
    Marketplace
    -0.82
     defekt
    -0.82
    POSITIVE LOGITS
     erforder
    0.94
     notwendi
    0.89
     voed
    0.88
     betreffenden
    0.87
     erforderlichen
    0.84
     notwendigen
    0.82
     traffico
    0.82
     persönliche
    0.81
     erreich
    0.81
     bisogno
    0.81
    Activations Density 0.000%

    No Known Activations