© 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. 109707
    Prev
    Next
    INDEX
    Explanations

    designer fashion brands

    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
     причиной
    -1.02
    }\}$
    -0.98
    tionen
    -0.88
    ٖ
    -0.82
     появля
    -0.81
     татуи
    -0.80
    inamento
    -0.79
     complicated
    -0.79
    ごとの
    -0.79
    LoadScene
    -0.78
    POSITIVE LOGITS
     collections
    1.09
     campaña
    0.91
    official
    0.90
     label
    0.89
    ：“……”
    0.88
     indef
    0.86
     公式
    0.86
    法則
    0.85
     Madras
    0.85
    ewear
    0.85
    Activations Density 0.025%

    No Known Activations