© 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. 103432
    Prev
    Next
    INDEX
    Explanations

    software and technical instructions

    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
     by
    -1.07
    fiques
    -1.02
    稱為
    -0.93
    软件特色
    -0.90
     pergola
    -0.90
     دیگران
    -0.90
     yana
    -0.85
    isyon
    -0.84
    dée
    -0.84
     mereka
    -0.84
    POSITIVE LOGITS
     för
    1.05
    }
    1.05
     luzes
    1.02
    茹で
    1.00
     için
    0.97
    emt
    0.96
     pentru
    0.96
     länder
    0.93
    Í
    0.92
     เพราะ
    0.91
    Activations Density 0.004%

    No Known Activations