© 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. 110491
    Prev
    Next
    INDEX
    Explanations

    next to or beside

    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
    Front
    -0.96
     تضيف
    -0.88
    front
    -0.86
    ⌐
    -0.85
    FRONT
    -0.85
    หลาย
    -0.84
    gericht
    -0.80
     FRONT
    -0.80
    LIS
    -0.79
     درمانی
    -0.79
    POSITIVE LOGITS
     accanto
    0.98
     Beside
    0.90
     beside
    0.88
     Each
    0.85
     insist
    0.82
     Besides
    0.82
     Alongside
    0.82
    やっぱ
    0.81
    marino
    0.81
    Besides
    0.80
    Activations Density 0.007%

    No Known Activations