© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 60522
    Prev
    Next
    INDEX
    Explanations

    object instance references

    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
     هذا
    -1.12
     этого
    -0.99
     حتی
    -0.98
     đây
    -0.98
     এই
    -0.97
     tässä
    -0.96
     الكويت
    -0.96
    降临
    -0.93
    giacca
    -0.93
     это
    -0.92
    POSITIVE LOGITS
     or
    0.97
    “
    0.96
    ulateur
    0.95
     again
    0.91
    assertSame
    0.90
     сыром
    0.89
    Again
    0.88
    .
    0.88
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.85
    ₨
    0.84
    Activations Density 0.003%

    No Known Activations