© 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. 25569
    Prev
    Next
    INDEX
    Explanations

    aspirations and future goals

    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
    有些不
    -1.22
     current
    -1.09
     currently
    -1.09
     necesarias
    -1.07
     permet
    -1.07
     funciona
    -1.03
     necesarios
    -1.00
     now
    -0.99
     unnecessarily
    -0.97
    now
    -0.96
    POSITIVE LOGITS
     someday
    1.67
    Someday
    1.22
     so
    1.11
     Eventually
    1.06
     dream
    0.98
    ÇÕES
    0.98
     Being
    0.95
     something
    0.95
    eventually
    0.94
     Ultimately
    0.94
    Activations Density 0.043%

    No Known Activations