© 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. 118792
    Prev
    Next
    INDEX
    Explanations

    code structure and content

    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
     so
    -1.10
     like
    -1.02
     not
    -0.95
     hogy
    -0.95
     könnten
    -0.94
    ächst
    -0.89
     preju
    -0.88
    𝗿
    -0.86
    Sebelum
    -0.85
     nicht
    -0.85
    POSITIVE LOGITS
     unseres
    1.01
    }</
    0.94
    }
    0.90
    verhältnisse
    0.89
    }\
    0.87
     Phosphorus
    0.86
     collapsible
    0.85
    ></
    0.85
    西装
    0.85
     }
    0.84
    Activations Density 0.021%

    No Known Activations