© 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. 112089
    Prev
    Next
    INDEX
    Explanations

    object, attribute, Array, Protocol, Manager, Labels, minimization

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

    compound words or class/variable names containing "Object" or "Source" in programming code.

    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
    ——”
    -1.78
     ruine
    -1.73
     huile
    -1.73
     gustaba
    -1.58
    」,
    -1.54
     duele
    -1.53
    lieving
    -1.45
    –)
    -1.44
     Departement
    -1.44
    ibility
    -1.42
    POSITIVE LOGITS
     here
    1.78
     and
    1.72
     supervivencia
    1.65
    ,
    1.59
    _
    1.57
     valoración
    1.52
     vooral
    1.52
     puntuación
    1.48
     either
    1.47
    UAWEI
    1.45
    Activations Density 0.027%

    No Known Activations