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. 7791
    Prev
    Next
    INDEX
    Explanations

    actions and deeds

    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
    ⊞
    -0.80
    EditorBrowsable
    -0.79
     CONTROLS
    -0.75
    疖
    -0.75
     Ciudad
    -0.75
    EndContext
    -0.75
    寿
    -0.74
    bedingt
    -0.73
    copies
    -0.72
    ifun
    -0.72
    POSITIVE LOGITS
     actions
    4.72
    actions
    3.80
    Actions
    3.67
     Actions
    3.67
     action
    3.63
     ACTIONS
    3.11
    ACTIONS
    2.86
     deeds
    2.84
    action
    2.78
     acciones
    2.75
    Activations Density 0.041%

    No Known Activations