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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-65K
    7. 4973
    Prev
    Next
    INDEX
    Explanations

    relatively little

    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
    built
    0.74
    assisted
    0.67
     سنه
    0.66
     Year
    0.66
    HIR
    0.66
    执
    0.64
    మాట
    0.64
    Established
    0.63
     guardar
    0.62
     रखेंगे
    0.61
    POSITIVE LOGITS
    <unused1074>
    0.85
    橹
    0.75
     commerce
    0.75
    <unused1772>
    0.75
    òng
    0.74
     Procter
    0.73
     microstructure
    0.71
     세
    0.71
    ouvement
    0.69
     comprising
    0.69
    Activations Density 0.002%

    No Known Activations