© 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
    5. 29-GEMMASCOPE-2-RES-16K
    7. 511
    Prev
    Next
    INDEX
    Explanations

    language models

    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
     prevalent
    0.88
     prevalence
    0.84
     commencement
    0.83
     linker
    0.82
     ហើយ
    0.82
    🈷
    0.81
     gestalt
    0.78
    너지
    0.77
     overtime
    0.76
     footpath
    0.76
    POSITIVE LOGITS
    <u>
    0.99
    <i>
    0.98
    <em>
    0.96
    <strong>
    0.96
    <b>
    0.89
    3
    0.87
    1
    0.85
    4
    0.85
    5
    0.83
    2
    0.82
    Activations Density 0.907%

    No Known Activations