© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 2119
    Prev
    Next
    INDEX
    Explanations

    multi-language technical terms

    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
    Takes
    2.11
     Takes
    1.90
     Pogis
    1.89
     карь
    1.86
     Exclusion
    1.82
     Concentrations
    1.75
     Moves
    1.74
    𝐡
    1.72
     Restrictions
    1.70
     Viewed
    1.69
    POSITIVE LOGITS
    vline
    1.66
    aal
    1.65
    fru
    1.61
    c
    1.59
    ار
    1.59
    zol
    1.59
     có
    1.55
    kul
    1.51
    czny
    1.51
    bildungs
    1.47
    Activations Density 0.000%

    No Known Activations