© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 891
    Prev
    Next
    INDEX
    Explanations

    ubuntu, chromatin, tweeter

    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
    -3.66
    a
    -2.69
    }{
    -2.66
    }$
    -2.53
     }),
    -2.47
     också
    -2.41
    }^{
    -2.30
    ↵↵
    -2.27
    )=
    -2.25
    ază
    -2.25
    POSITIVE LOGITS
    但她
    2.84
    0
    2.81
    on
    2.55
    蘗
    2.53
    𐄁
    2.45
    
    2.31
    了起来
    2.30
     وہ
    2.23
     utilizamos
    2.22
    because
    2.20
    Activations Density 0.034%

    No Known Activations