© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 11817
    Prev
    Next
    INDEX
    Explanations

    conversations about memory

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_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
    
    3.32
    
    3.19
    
    3.19
    
    3.04
    <bos>
    2.92
    
    2.90
    ⁣⁣
    2.87
    \".
    2.86
    ২১
    2.82
     
    2.62
    POSITIVE LOGITS
    er
    3.95
    ar
    3.93
    al
    3.62
    ي
    3.51
    a
    3.40
    atkar
    3.15
    e
    3.13
    د
    3.09
    ার
    2.98
    ی
    2.95
    Activations Density 0.002%

    No Known Activations