© 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. 110639
    Prev
    Next
    INDEX
    Explanations

    under select fields

    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
    자인
    -0.98
    estors
    -0.94
    λιά
    -0.90
    thalle
    -0.88
    tki
    -0.88
     enfri
    -0.88
     derra
    -0.88
    Fakta
    -0.88
    ρούν
    -0.87
    Setiap
    -0.86
    POSITIVE LOGITS
     under
    1.31
     Type
    1.07
    勾
    1.03
     Under
    1.02
     fields
    1.02
     leave
    1.01
     field
    1.00
     Name
    0.98
     Select
    0.94
     here
    0.93
    Activations Density 0.073%

    No Known Activations