© 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. 119935
    Prev
    Next
    INDEX
    Explanations

    nothing to do with

    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
     também
    -1.44
    </h1>
    -1.42
     også
    -1.38
    ції
    -1.36
    と同じ
    -1.34
     också
    -1.34
    certain
    -1.30
     garantías
    -1.30
     also
    -1.29
     Übersetzungen
    -1.27
    POSITIVE LOGITS
     whatsoever
    1.33
     sparkly
    1.27
     which
    1.23
    ืน
    1.22
     Those
    1.21
     providing
    1.21
     or
    1.19
     sauté
    1.19
    Thanos
    1.18
     الصد
    1.17
    Activations Density 0.032%

    No Known Activations