© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 38663
    Prev
    Next
    INDEX
    Explanations

    child elements

    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_10/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
     trebui
    -1.48
     utilizó
    -1.48
     reseña
    -1.47
    pueden
    -1.47
     it
    -1.45
    が欲しい
    -1.43
     sabido
    -1.41
     solicitó
    -1.35
     they
    -1.34
     asesinado
    -1.32
    POSITIVE LOGITS
     of
    2.06
     zama
    1.44
     –
    1.44
     samh
    1.35
     caoutchouc
    1.27
    )$.
    1.25
    )=\
    1.24
    gazione
    1.24
    CHREIBUNG
    1.23
     mera
    1.21
    Activations Density 0.004%

    No Known Activations