© 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. 110580
    Prev
    Next
    INDEX
    Explanations

    size, count, length

    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
    來說
    -0.85
    őtt
    -0.80
    colate
    -0.79
    Kosten
    -0.77
    sira
    -0.75
    ServiceProvider
    -0.75
     trained
    -0.75
    ۪
    -0.75
    ths
    -0.74
    urer
    -0.74
    POSITIVE LOGITS
     count
    1.95
     length
    1.76
     Count
    1.59
    Count
    1.45
    count
    1.45
     len
    1.38
     Length
    1.27
    len
    1.20
     COUNT
    1.19
     size
    1.15
    Activations Density 0.028%

    No Known Activations