© 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. 118735
    Prev
    Next
    INDEX
    Explanations

    project design client

    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
    ݨ
    -0.88
     wykor
    -0.83
     caminhão
    -0.81
    ="/">
    -0.81
    uelos
    -0.81
    щены
    -0.79
    óval
    -0.79
     cuento
    -0.79
    úcia
    -0.78
    頷
    -0.78
    POSITIVE LOGITS
     client
    1.31
    CLIENT
    1.30
     drawings
    1.23
     Client
    1.20
     design
    1.13
     Clients
    1.13
    client
    1.12
     clients
    1.08
     project
    1.06
     budget
    1.06
    Activations Density 0.012%

    No Known Activations