© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 451
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ’
    1.23
    ,
    1.21
     of
    1.16
    .
    1.13
     and
    1.13
     in
    1.07
    -
    1.01
     is
    0.94
     has
    0.94
     και
    0.93
    POSITIVE LOGITS
    শংস
    1.44
    ото
    1.34
    रुख
    1.23
     vosotros
    1.23
    م
    1.22
    koľ
    1.22
    छि
    1.22
     ваших
    1.22
     длину
    1.21
    ونَ
    1.21
    Activations Density 0.606%

    No Known Activations