© 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. 11694
    Prev
    Next
    INDEX
    Explanations

    training sessions and programs

    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
    PRF
    2.92
    शंकर
    2.79
     теле
    2.76
    
    2.75
    
    2.68
    ˶
    2.67
    За
    2.63
    galax
    2.62
    Inst
    2.61
    sgál
    2.59
    POSITIVE LOGITS
    o
    3.07
    iye
    2.88
    l
    2.85
    aar
    2.77
    ož
    2.75
    潟
    2.66
    i
    2.65
    া
    2.64
    ം
    2.63
    rå
    2.61
    Activations Density 0.070%

    No Known Activations