© 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. 67629
    Prev
    Next
    INDEX
    Explanations

    names and places in England

    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
     stär
    -2.77
     для
    -2.75
    derdag
    -2.56
    찮
    -2.55
     weißen
    -2.47
     für
    -2.47
     Ersten
    -2.47
     Physically
    -2.41
    s
    -2.38
    e
    -2.36
    POSITIVE LOGITS
    蘩
    3.28
    ༀ
    3.20
    猡
    2.98
    聍
    2.95
    the
    2.92
    轵
    2.81
    ፨
    2.72
    \
    2.66
     üçün
    2.66
    .
    2.64
    Activations Density 0.020%

    No Known Activations