© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 86153
    Prev
    Next
    INDEX
    Explanations

    i. or i)

    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
    ↵
    -4.44
    ↵↵
    -4.28
    D
    -3.81
    With
    -3.52
     
    -3.45
    C
    -3.41
    <i>
    -3.31
    to
    -3.22
    2
    -3.14
    <b>
    -3.13
    POSITIVE LOGITS
     was
    3.41
    驺
    3.22
    黉
    3.22
    鲼
    3.20
    艄
    3.19
    饪
    3.13
    蚍
    3.05
    韡
    3.03
     dezelve
    2.98
    
    2.98
    Activations Density 0.028%

    No Known Activations