© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 99639
    Prev
    Next
    INDEX
    Explanations

    Otis, exon, Conor McGregor, Barr Scott

    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
     Some
    -3.09
     großen
    -2.88
    ዌ
    -2.66
     größeren
    -2.55
    Ꭳ
    -2.52
    闳
    -2.41
    byshev
    -2.39
    vantaged
    -2.38
     terwijl
    -2.36
     oberen
    -2.33
    POSITIVE LOGITS
    2
    3.20
    辚
    2.56
    缡
    2.48
    甃
    2.41
    q
    2.41
    }
    2.36
    a
    2.34
    ꪹ
    2.33
    traueranzeige
    2.27
    x
    2.27
    Activations Density 0.016%

    No Known Activations