© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 54220
    Prev
    Next
    INDEX
    Explanations

    titles and headings

    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
     volverá
    -1.44
    Leírás
    -1.09
     échou
    -1.08
    确实是
    -1.06
     décrit
    -1.03
     évo
    -1.02
     feltro
    -1.02
    ឋ
    -1.02
     quedará
    -1.00
     agarre
    -0.99
    POSITIVE LOGITS
    lores
    0.97
     to
    0.93
    ，
    0.91
    <td>
    0.90
    ful
    0.90
    Must
    0.86
    \}\\
    0.86
    kezik
    0.84
    ——
    0.84
    must
    0.84
    Activations Density 0.001%

    No Known Activations