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. 7500
    Prev
    Next
    INDEX
    Explanations

    state management in redux

    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
     nii
    -0.78
    ötet
    -0.76
    довые
    -0.76
     GUAR
    -0.75
     SENIOR
    -0.75
     konge
    -0.72
    responseBody
    -0.72
    Sous
    -0.72
    galaxy
    -0.71
     Kuns
    -0.71
    POSITIVE LOGITS
     state
    2.50
    state
    1.80
     initialState
    1.77
     states
    1.65
     State
    1.53
    getState
    1.48
    STATE
    1.48
    initialState
    1.43
     estado
    1.43
    State
    1.41
    Activations Density 0.012%

    No Known Activations