© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 14311
    Prev
    Next
    INDEX
    Explanations

    api versions (v1, v2)

    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
     then
    -1.61
     lavora
    -1.48
     моих
    -1.44
     construida
    -1.42
     destinada
    -1.42
     but
    -1.41
     experimentado
    -1.39
    ーん
    -1.37
     económica
    -1.35
     geomé
    -1.35
    POSITIVE LOGITS
     of
    2.34
    \{
    1.39
     \
    1.32
    При
    1.29
    пион
    1.28
    )$,
    1.24
    部に
    1.23
    }$,
    1.21
     $
    1.21
    ceğiniz
    1.20
    Activations Density 0.012%

    No Known Activations