© 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. 112463
    Prev
    Next
    INDEX
    Explanations

    place names or cities

    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
     titolata
    -1.82
     Він
    -1.81
    ፨
    -1.77
     тази
    -1.75
    ataires
    -1.73
     使っ
    -1.73
    なんですが
    -1.73
     ujedno
    -1.71
     malattia
    -1.67
     with
    -1.66
    POSITIVE LOGITS
    (
    2.50
    </strong>
    2.27
    /
    2.20
    "
    2.19
    -
    2.11
    ،
    2.00
    i
    1.94
     are
    1.87
    ."
    1.86
    ("
    1.85
    Activations Density 0.039%

    No Known Activations