© 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
    5. 29-GEMMASCOPE-2-RES-16K
    7. 2164
    Prev
    Next
    INDEX
    Explanations

    data points, his field, copyright

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-pt/resid_post/layer_29_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    銠
    0.93
    鉞
    0.89
    <unused34>
    0.82
    รียน
    0.81
     españoles
    0.80
    ኵ
    0.80
     TRANSPORTURI
    0.79
     basilaires
    0.79
    鰱
    0.79
    <unused87>
    0.78
    POSITIVE LOGITS
     t
    1.94
    <unused61>
    1.77
     whi
    1.76
     р
    1.72
     s
    1.68
     p
    1.67
     wi
    1.67
     hea
    1.62
     н
    1.62
    <unused62>
    1.60
    Activations Density 1.067%

    No Known Activations