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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 33751
    Prev
    Next
    INDEX
    Explanations

    //, ----- , *

    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_22/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
    ⑉
    -1.75
     Tratado
    -1.63
    ꉂ
    -1.62
    imbang
    -1.55
     Tän
    -1.55
    jika
    -1.51
     terkenal
    -1.47
    Neden
    -1.46
     Países
    -1.45
     bénéfice
    -1.45
    POSITIVE LOGITS
    ↵
    2.00
    an
    1.73
    al
    1.68
    U
    1.63
    n
    1.61
    </i>
    1.59
    d
    1.55
    T
    1.53
    ist
    1.52
    g
    1.51
    Activations Density 0.013%

    No Known Activations