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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 109720
    Prev
    Next
    INDEX
    Explanations

    Eugenie, Eugenia names

    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
     rivi
    -0.86
     trad
    -0.81
    キュー
    -0.80
     يج
    -0.77
     PRIV
    -0.77
    ু
    -0.76
    тической
    -0.75
    tum
    -0.73
     заяви
    -0.71
     grieve
    -0.71
    POSITIVE LOGITS
    mounted
    0.85
    斕
    0.82
    hláš
    0.79
    rentina
    0.79
    elementary
    0.77
    櫟
    0.77
    ratulations
    0.77
    nullptr
    0.76
    omics
    0.76
    Feeding
    0.76
    Activations Density 0.073%

    No Known Activations