© 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. 22-GEMMASCOPE-RES-131K
    4. 39793
    Prev
    Next
    INDEX
    Explanations

    code includes and Q&A

    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_22/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
    izacja
    -0.84
     Vorbe
    -0.80
    াম
    -0.79
    gulation
    -0.79
     беже
    -0.79
    isten
    -0.76
    bots
    -0.76
     Penelitian
    -0.75
     principio
    -0.75
    MethodInfo
    -0.74
    POSITIVE LOGITS
     instead
    0.93
     skall
    0.88
    `),
    0.87
     istället
    0.84
    '),
    0.84
    でしたが
    0.84
     dezvol
    0.83
     gulls
    0.82
     },
    0.82
     Superhost
    0.81
    Activations Density 0.012%

    No Known Activations