© 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. 85265
    Prev
    Next
    INDEX
    Explanations

    rsp, Celtics, MySql, Erdos, PIC

    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
    i
    -4.34
    8
    -3.56
    6
    -3.53
    -
    -3.44
                    
    -3.41
    7
    -3.33
    9
    -3.33
    2
    -3.30
    4
    -3.14
    3
    -3.13
    POSITIVE LOGITS
     kteří
    3.06
    떳
    2.98
    接下来的
    2.98
     >",
    2.97
    铼
    2.89
    Ꮵ
    2.88
    羋
    2.81
    赑
    2.78
     drit
    2.73
    戆
    2.72
    Activations Density 0.027%

    No Known Activations