© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-65K
    7. 338
    Prev
    Next
    INDEX
    Explanations

    section introductions

    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_13_width_65k_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
     /
    1.27
     (
    1.22
    /
    1.21
    ,
    1.18
     ,
    1.09
     of
    1.05
     was
    1.04
    -
    1.02
     (?)
    1.01
     -
    0.98
    POSITIVE LOGITS
    Challenges
    1.76
    Bringing
    1.74
    Getting
    1.74
    Connecting
    1.73
    Creating
    1.66
    Exploring
    1.58
    Putting
    1.58
    Making
    1.57
    Becoming
    1.56
    Choosing
    1.55
    Activations Density 0.555%

    No Known Activations