© 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. 84862
    Prev
    Next
    INDEX
    Explanations

    funding for programs opportunities

    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
    s
    -3.20
    '
    -3.06
    猻
    -2.39
    )」
    -2.34
    孥
    -2.33
    and
    -2.31
    自
    -2.27
    作品
    -2.27
    」。
    -2.22
    箜
    -2.20
    POSITIVE LOGITS
    鸶
    4.06
    趼
    3.25
    沨
    3.02
    觏
    2.61
    
    2.59
    靣
    2.58
    諏
    2.58
    薆
    2.56
     Their
    2.50
    我没
    2.47
    Activations Density 0.005%

    No Known Activations