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. 7783
    Prev
    Next
    INDEX
    Explanations

    peeling off protective layers

    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
     pungkasnya
    -0.69
     Navarro
    -0.68
    Lug
    -0.67
     bahç
    -0.66
    _{+
    -0.66
     dolayı
    -0.65
     condiv
    -0.64
     caja
    -0.64
    idenav
    -0.64
    bok
    -0.63
    POSITIVE LOGITS
     protective
    2.36
     Protective
    2.13
    protective
    2.06
    Protective
    1.99
     protecting
    1.37
    保護
    1.33
     protectors
    1.30
     защи
    1.28
     backing
    1.27
     sticker
    1.26
    Activations Density 0.031%

    No Known Activations