© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 72015
    Prev
    Next
    INDEX
    Explanations

    quotes and names

    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
    När
    -1.38
     décé
    -1.33
    də
    -1.27
     великолеп
    -1.24
    ݣ
    -1.19
    Efter
    -1.17
    during
    -1.15
     hva
    -1.15
    nische
    -1.14
    På
    -1.13
    POSITIVE LOGITS
    :
    1.22
     for
    1.17
    ↵
    1.16
    "
    1.16
    !
    1.15
     in
    1.08
     نیز
    1.01
     that
    0.99
    .
    0.98
    就可以了
    0.97
    Activations Density 0.002%

    No Known Activations