© 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. 59833
    Prev
    Next
    INDEX
    Explanations

    pussy

    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
    T
    -3.98
    “
    -3.98
    B
    -3.72
    2
    -3.34
    h
    -3.27
    V
    -3.23
    The
    -2.98
     have
    -2.98
    S
    -2.95
    1
    -2.92
    POSITIVE LOGITS
    ೣ
    2.77
    銠
    2.66
     navires
    2.45
    ޑ
    2.44
    ᠂
    2.42
    罍
    2.41
    檮
    2.39
    鷙
    2.38
    蟶
    2.38
    และ
    2.34
    Activations Density 0.003%

    No Known Activations