© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 666
    Prev
    Next
    INDEX
    Explanations

    graphviz, sourcegraph, RLgraph

    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
    čkou
    -0.84
     Wt
    -0.81
     竹
    -0.76
     ambao
    -0.71
    ntl
    -0.71
     기
    -0.70
     homogeneous
    -0.69
     cahaya
    -0.68
    igten
    -0.68
     Zusammen
    -0.68
    POSITIVE LOGITS
     subgraph
    0.85
    споль
    0.78
    幸運
    0.75
    ностран
    0.74
     missions
    0.74
    errcode
    0.73
    诶
    0.72
    getObject
    0.71
    ὸ
    0.71
    ivamente
    0.70
    Activations Density 0.022%

    No Known Activations