© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 640
    Prev
    Next
    INDEX
    Explanations

    function `main` `test` `bar`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     for
    -1.70
     Paesi
    -1.22
     of
    -1.13
     *}
    -1.12
     \%}$
    -1.09
    ूरत
    -1.08
    Xoa
    -1.06
    璝
    -1.05
    യും
    -1.05
    эф
    -1.05
    POSITIVE LOGITS
    4
    1.30
     Commencez
    1.22
    Gilla
    1.20
     añadido
    1.20
     things
    1.19
     sustituir
    1.18
    2
    1.16
     Using
    1.16
     quiso
    1.15
     esclavos
    1.13
    Activations Density 0.376%

    No Known Activations