© 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. 22-GEMMASCOPE-RES-131K
    7. 33856
    Prev
    Next
    INDEX
    Explanations

    helping and sharing with others

    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_22/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
     themselves
    -1.24
    Their
    -1.13
    他們的
    -1.09
    讓我們
    -1.09
     pulmonar
    -1.04
    ]^{
    -1.03
    他们在
    -1.02
     leurs
    -1.01
     possuem
    -1.01
     белого
    -1.00
    POSITIVE LOGITS
     my
    2.58
     myself
    1.71
     people
    1.69
     someday
    1.45
     hopefully
    1.33
     others
    1.27
     mensen
    1.27
     helping
    1.24
    𝑈
    1.23
     help
    1.19
    Activations Density 0.027%

    No Known Activations