© 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. 75405
    Prev
    Next
    INDEX
    Explanations

    conventional or unconventional

    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
    明显的
    -1.38
    镲
    -1.38
    cześ
    -1.36
    塍
    -1.36
    ⑊
    -1.34
    somebody
    -1.31
    tichetta
    -1.31
     Unii
    -1.29
     ſeveral
    -1.29
    ちな
    -1.29
    POSITIVE LOGITS
     at
    1.43
     While
    1.42
     first
    1.38
    ଞ
    1.38
     methods
    1.34
     unconventional
    1.33
    hmigung
    1.30
     shortly
    1.30
     immediately
    1.30
    ad
    1.29
    Activations Density 0.037%

    No Known Activations