© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 82615
    Prev
    Next
    INDEX
    Explanations

    Combinatorial or ring discussions

    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
    链接
    -0.77
    只剩下
    -0.77
     несмотря
    -0.77
    čila
    -0.75
     GE
    -0.73
    นะ
    -0.73
    lenia
    -0.73
    cjon
    -0.73
     conni
    -0.73
    gste
    -0.72
    POSITIVE LOGITS
     étions
    0.82
     Ruk
    0.81
     maaaring
    0.78
     parlant
    0.77
    Orlando
    0.76
     willkommen
    0.74
     Rukh
    0.74
     Cracking
    0.73
    λει
    0.73
    asyncio
    0.73
    Activations Density 0.008%

    No Known Activations