© 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-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-65K
    7. 5176
    Prev
    Next
    INDEX
    Explanations

    how to proceed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     others
    0.80
     expressed
    0.79
     calculating
    0.77
     calculate
    0.74
     Calculating
    0.73
     calculation
    0.68
     expressing
    0.68
     (%)
    0.68
     division
    0.67
     calculated
    0.66
    POSITIVE LOGITS
     Sulfate
    0.89
     naszego
    0.88
    Sulf
    0.83
     Recordemos
    0.83
    0.82
    0.82
     tempHeader
    0.81
    Guidelines
    0.79
    আমাদের
    0.78
    我们的
    0.77
    Activations Density 0.261%

    No Known Activations