© 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. 11756
    Prev
    Next
    INDEX
    Explanations

    flushing, rosy, pink colors

    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
    j
    -1.46
    m
    -1.34
    ”？
    -1.30
    ke
    -1.27
    </sup>
    -1.25
    po
    -1.24
    v
    -1.24
    ؛
    -1.23
    printf
    -1.21
    zi
    -1.20
    POSITIVE LOGITS
    spricht
    1.40
    渕
    1.32
    ↵
    1.32
     calificación
    1.23
     empiezan
    1.21
     obstáculos
    1.20
    Emerald
    1.19
     asociación
    1.19
    нев
    1.18
     heiß
    1.16
    Activations Density 0.127%

    No Known Activations