© 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. 15181
    Prev
    Next
    INDEX
    Explanations

    Shen names and locations

    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
    眼下
    -2.63
    烔
    -2.52
    してい
    -2.44
    𖥦
    -2.42
    乆
    -2.41
     остается
    -2.33
    更高的
    -2.31
    沇
    -2.31
    骝
    -2.31
    詒
    -2.30
    POSITIVE LOGITS
    {
    2.81
    ใน
    2.41
     क्योंकि
    2.38
    }
    2.36
    \
    2.28
     錠
    2.20
    在
    2.19
     другими
    2.16
     ſont
    2.08
     मदद
    2.03
    Activations Density 0.001%

    No Known Activations