© 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. 112706
    Prev
    Next
    INDEX
    Explanations

    . or $

    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
    )
    -1.51
     Eſ
    -1.43
    toThrow
    -1.41
    化妆
    -1.35
    hence
    -1.30
     BEAUT
    -1.29
     difer
    -1.29
    Unable
    -1.28
    ⌊
    -1.27
    この
    -1.25
    POSITIVE LOGITS
    ASONS
    1.85
    ânico
    1.72
    好用
    1.67
     with
    1.66
    ↵
    1.66
     including
    1.59
     using
    1.55
     którzy
    1.47
     continued
    1.45
     many
    1.42
    Activations Density 0.102%

    No Known Activations