© 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. 118664
    Prev
    Next
    INDEX
    Explanations

    the number 1

    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
    Зно
    -1.00
    ѯ
    -0.91
     сожа
    -0.90
    嘮
    -0.90
    attore
    -0.90
    geslacht
    -0.90
    StringCopy
    -0.89
    ÑOS
    -0.88
     знать
    -0.88
    ilderness
    -0.88
    POSITIVE LOGITS
    λυ
    1.02
    קס
    0.99
    ledes
    0.98
     verdo
    0.98
    laterra
    0.92
    ТА
    0.92
    къ
    0.92
    ~~~~~~~
    0.92
    ″
    0.92
     dissenting
    0.91
    Activations Density 0.062%

    No Known Activations