© 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. 110424
    Prev
    Next
    INDEX
    Explanations

    code syntax elements

    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
    tový
    -0.94
     großes
    -0.91
     myös
    -0.91
     하는
    -0.89
     melakukan
    -0.87
     liefde
    -0.87
     jeszcze
    -0.85
    ้งาน
    -0.85
     _$
    -0.84
    SqlConnection
    -0.84
    POSITIVE LOGITS
    iciaries
    0.88
     („
    0.83
     помогает
    0.73
     Schreib
    0.73
     детстве
    0.72
    というのも
    0.71
     rappel
    0.71
     prestation
    0.71
    erobic
    0.70
    ÚBL
    0.70
    Activations Density 0.004%

    No Known Activations