© 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. 99613
    Prev
    Next
    INDEX
    Explanations

    a followed by descriptive noun

    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
    addCriterion
    -1.45
    家が
    -1.41
    DebuggerNonUser
    -1.38
    GOTREF
    -1.35
    enterOuterAlt
    -1.34
    CodeAttribute
    -1.27
    EReference
    -1.27
     respald
    -1.22
    béco
    -1.22
    aarrggbb
    -1.22
    POSITIVE LOGITS
    )
    1.42
    </b>
    1.39
    美味しかった
    1.30
    probably
    1.27
    apparently
    1.23
     zwei
    1.22
    currently
    1.21
     gain
    1.19
     praktische
    1.16
     deux
    1.16
    Activations Density 0.132%

    No Known Activations