© 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. 118742
    Prev
    Next
    INDEX
    Explanations

    upfront costs and locations

    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
     running
    -2.42
     runs
    -2.39
    running
    -2.20
     run
    -2.14
    Running
    -2.00
     Running
    -1.90
    RUNNING
    -1.89
     Runs
    -1.86
    Runs
    -1.84
    runs
    -1.83
    POSITIVE LOGITS
    front
    2.13
     front
    1.97
    FRONT
    1.77
     Front
    1.68
    Front
    1.66
     fronts
    1.51
     FRONT
    1.35
     фрон
    1.20
    ront
    1.20
    フロント
    1.13
    Activations Density 0.068%

    No Known Activations