© 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. 321
    Prev
    Next
    INDEX
    Explanations

    actually followed by verb

    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
    //
    -1.64
    一些
    -1.54
    0
    -1.47
    }
    -1.38
     САД
    -1.36
     aprobación
    -1.34
    不要
    -1.34
    A
    -1.34
    زندگی
    -1.33
    /
    -1.33
    POSITIVE LOGITS
    ,’
    1.52
    </em>
    1.48
    altet
    1.45
    مزید
    1.35
    drav
    1.35
    軋
    1.34
    tricos
    1.34
     same
    1.32
     TAMBIÉN
    1.30
    سطس
    1.27
    Activations Density 0.011%

    No Known Activations