© 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
    2. Gemma-3-1B
    3. 7-GEMMASCOPE-2-RES-16K
    4. 1273
    Prev
    Next
    INDEX
    Explanations

    by or de before names

    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
    ,
    1.83
     for
    1.78
     of
    1.76
     to
    1.73
     on
    1.67
     in
    1.65
    _
    1.61
     with
    1.58
    -
    1.57
    oelectric
    1.57
    POSITIVE LOGITS
     nonché
    2.63
     témoign
    2.55
    ⧐
    2.39
     destaque
    2.37
     confronto
    2.32
     quốc
    2.31
     giám
    2.26
     σημ
    2.26
     órgão
    2.24
     ipotesi
    2.23
    Activations Density 0.316%

    No Known Activations