© 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. 45109
    Prev
    Next
    INDEX
    Explanations

    London and California place names

    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
    他的
    -2.03
    no
    -1.87
     viser
    -1.83
    me
    -1.83
     they
    -1.79
    是
    -1.79
    O
    -1.70
    我的
    -1.68
     patienter
    -1.67
    name
    -1.65
    POSITIVE LOGITS
    }$
    2.05
     You
    1.94
    scrollPane
    1.70
     欣赏
    1.59
     specjal
    1.57
    但不
    1.56
     dargestellt
    1.55
     dicen
    1.55
     mezcla
    1.53
    PvB
    1.52
    Activations Density 0.008%

    No Known Activations