© 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. 1285
    Prev
    Next
    INDEX
    Explanations

    complex social issues and difficulties

    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
    of
    1.04
    ,
    0.96
    )
    0.92
    -
    0.92
    or
    0.90
    .
    0.90
    offer
    0.89
    ois
    0.88
    endre
    0.87
    j
    0.87
    POSITIVE LOGITS
     гораздо
    2.41
     incredibly
    2.32
     terribly
    2.32
     ridiculously
    2.29
     roughly
    2.28
     tremendous
    2.27
     намного
    2.25
     considerably
    2.25
     considerable
    2.23
     znacznie
    2.22
    Activations Density 0.760%

    No Known Activations