© 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. 128418
    Prev
    Next
    INDEX
    Explanations

    emphasized word or phrase start

    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
     this
    -1.23
    Mitglied
    -1.07
     akum
    -1.06
     kunjung
    -1.03
    這款
    -1.03
     pietre
    -1.02
     piscinas
    -0.98
     Suomessa
    -0.97
    zelfde
    -0.96
     Consum
    -0.96
    POSITIVE LOGITS
     for
    1.31
     to
    1.25
     because
    1.13
     not
    1.12
     that
    1.03
     of
    1.03
    !
    1.01
    N
    0.99
     means
    0.99
     Redaktion
    0.97
    Activations Density 0.026%

    No Known Activations