© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 130743
    Prev
    Next
    INDEX
    Explanations

    walking around and through places

    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
    </td>
    -1.68
     joaat
    -1.38
    醞
    -1.37
     o
    -1.34
     y
    -1.32
     you
    -1.32
     undertake
    -1.31
     当
    -1.30
     Sadly
    -1.28
    两个
    -1.27
    POSITIVE LOGITS
     of
    1.95
     طرق
    1.37
    짠
    1.34
     raad
    1.29
     cauſe
    1.28
     コレクション
    1.24
     海岸
    1.23
    syd
    1.21
     cepillo
    1.20
    妧
    1.20
    Activations Density 0.021%

    No Known Activations