Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8717
    Prev
    Next
    INDEX
    Explanations

    types of environment

    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
    Andrey
    -0.70
    Díky
    -0.70
    Javier
    -0.68
    階
    -0.66
    ueuse
    -0.66
     ۹
    -0.66
    </thead>
    -0.66
    列車
    -0.65
     doable
    -0.64
    calypse
    -0.64
    POSITIVE LOGITS
     environment
    3.20
     environments
    2.17
    environment
    1.95
     Environment
    1.82
    环境
    1.78
    Environment
    1.78
     env
    1.73
     ENVIRONMENT
    1.71
     ambiente
    1.64
     lingkungan
    1.63
    Activations Density 0.125%

    No Known Activations