© 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. 10-GEMMASCOPE-RES-131K
    7. 59655
    Prev
    Next
    INDEX
    Explanations

    Official documents and identification

    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
     desse
    -1.40
     temas
    -1.31
     efec
    -1.25
     définition
    -1.23
    笮
    -1.23
     molto
    -1.23
     efic
    -1.21
     latas
    -1.21
     comprando
    -1.20
    罍
    -1.20
    POSITIVE LOGITS
     from
    1.77
     if
    1.60
     or
    1.28
     of
    1.23
     Lengkap
    1.23
    ordonnées
    1.16
     Traditionally
    1.16
     that
    1.14
     jeśli
    1.13
     Sebelum
    1.13
    Activations Density 0.025%

    No Known Activations