© 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. 84730
    Prev
    Next
    INDEX
    Explanations

    proper names or BMI

    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
    \
    -2.50
    饪
    -2.45
    }
    -2.42
    ሖ
    -2.42
    "
    -2.38
    禤
    -2.27
    𝟮
    -2.27
    at
    -2.27
    .《
    -2.14
    .
    -2.08
    POSITIVE LOGITS
    that
    2.83
    Descri
    2.66
     что
    2.58
    皤
    2.47
     که
    2.44
    菝
    2.39
     unsere
    2.38
    ーーーー
    2.34
    鉿
    2.28
    ༆
    2.20
    Activations Density 0.003%

    No Known Activations