© 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. 59448
    Prev
    Next
    INDEX
    Explanations

    being freed from

    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
     But
    -1.52
    ↵↵
    -1.38
    痺
    -1.38
    韮
    -1.38
    ânica
    -1.36
    .
    -1.34
    縞
    -1.34
    -1.32
     justifyContent
    -1.32
     xícara
    -1.30
    POSITIVE LOGITS
    Jahre
    1.66
     müm
    1.56
    也可以
    1.54
    лением
    1.51
    也有
    1.48
    蟜
    1.45
    都是
    1.42
     tarafından
    1.41
    觅
    1.41
     Poids
    1.41
    Activations Density 0.019%

    No Known Activations