© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 111642
    Prev
    Next
    INDEX
    Explanations

    storage area network (SAN) and outsourcing

    np_acts-logits-general · gemini-2.5-flash-lite

    technical and business terms related to IT infrastructure, storage systems, and service-based pricing models.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     Forderung
    -1.24
     magari
    -1.20
    umenten
    -1.14
     orizz
    -1.11
     Fähigkeit
    -1.11
    mingo
    -1.11
    Etimología
    -1.10
     желания
    -1.09
     "'";
    -1.09
     Absicht
    -1.07
    POSITIVE LOGITS
     without
    1.32
    $
    1.17
     with
    1.15
     duide
    1.06
    <i>
    1.06
     more
    1.04
     奈
    1.02
     egentligen
    1.02
     would
    1.02
    했
    1.02
    Activations Density 0.107%

    No Known Activations