© 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. 34-GEMMASCOPE-RES-131K
    7. 118159
    Prev
    Next
    INDEX
    Explanations

    documentation entry points

    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_34/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
    🤺
    -0.78
    czaj
    -0.76
     ihan
    -0.76
    ✾
    -0.75
     редко
    -0.74
    ċ
    -0.73
     mahd
    -0.73
    IDTH
    -0.73
     Worte
    -0.72
     merek
    -0.72
    POSITIVE LOGITS
     fired
    0.86
     kennen
    0.78
     Fired
    0.77
    ěr
    0.77
     swings
    0.74
    ᐛ
    0.74
    插
    0.73
     Parton
    0.72
    とう
    0.72
     echoed
    0.72
    Activations Density 0.005%

    No Known Activations