Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8696
    Prev
    Next
    INDEX
    Explanations

    anti-

    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
     ”
    -1.30
    техни
    -1.30
     nästan
    -1.24
     –
    -1.21
    ето
    -1.20
     ""],
    -1.20
     berichten
    -1.17
     förra
    -1.16
     “(
    -1.16
    мини
    -1.16
    POSITIVE LOGITS
     також
    1.39
    colori
    1.30
     также
    1.30
    Cierre
    1.27
    ところに
    1.26
    ようで
    1.21
     necessary
    1.20
    會
    1.19
     same
    1.19
     будет
    1.18
    Activations Density 0.083%

    No Known Activations