© 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. 72924
    Prev
    Next
    INDEX
    Explanations

    consequently or correspondingly

    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
    नलोड
    -1.58
     on
    -1.55
     still
    -1.52
    </strong>
    -1.42
    levance
    -1.39
     jeho
    -1.39
     четыре
    -1.39
    èdent
    -1.34
     М
    -1.33
    人体
    -1.33
    POSITIVE LOGITS
     دیگر
    1.52
    _
    1.48
    更何况
    1.40
    figure
    1.30
     選択
    1.28
     peux
    1.27
     reduziert
    1.27
     陳
    1.27
    次回は
    1.27
     fhe
    1.26
    Activations Density 0.022%

    No Known Activations