© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 90796
    Prev
    Next
    INDEX
    Explanations

    words like hilarious

    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
    ㉗
    -3.22
    摇了
    -2.70
     algunas
    -2.59
     всѣ
    -2.58
     nuestro
    -2.52
    譟
    -2.41
    t
    -2.39
    м
    -2.38
    ㉕
    -2.34
    比べて
    -2.33
    POSITIVE LOGITS
    .
    3.69
    that
    2.84
    ness
    2.28
     amounts
    2.19
    鬭
    2.16
    あっという間に
    2.11
    $
    2.09
    ity
    2.05
    }
    2.03
    一旁
    2.02
    Activations Density 0.001%

    No Known Activations