© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-65K
    7. 2990
    Prev
    Next
    INDEX
    Explanations

    example

    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
     sensitively
    0.72
     onerous
    0.68
     munitions
    0.68
    瑢
    0.67
    嬷
    0.66
     affluent
    0.66
     formatos
    0.64
     젊
    0.64
    Denote
    0.63
    Formats
    0.63
    POSITIVE LOGITS
     example
    2.15
    example
    1.97
     Example
    1.90
    Example
    1.83
     ejemplo
    1.81
    示例
    1.78
     exemplo
    1.77
     examples
    1.72
     exemple
    1.72
     esempio
    1.71
    Activations Density 0.829%

    No Known Activations