© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 118749
    Prev
    Next
    INDEX
    Explanations

    . Series, Value, Text, Items

    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
    malla
    -0.78
     orgull
    -0.76
     HttpRequest
    -0.75
    เหร
    -0.73
     소녀
    -0.73
    싶
    -0.73
     Shaping
    -0.72
    ują
    -0.72
     fiyatı
    -0.72
     suminist
    -0.71
    POSITIVE LOGITS
    Tag
    1.05
    Invoke
    1.02
     Tag
    0.98
    Controls
    0.87
     this
    0.83
    Parent
    0.80
     Controls
    0.79
    DataSource
    0.77
    TAG
    0.76
    टे
    0.76
    Activations Density 0.037%

    No Known Activations