© 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. 34-GEMMASCOPE-RES-131K
    4. 38364
    Prev
    Next
    INDEX
    Explanations

    this followed by label

    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
     visse
    -1.09
     déterminer
    -1.05
     Europas
    -1.00
     Grafik
    -0.96
     jezt
    -0.96
     berlin
    -0.96
     Berat
    -0.95
     Ucraina
    -0.94
    ynnwys
    -0.94
     شان
    -0.93
    POSITIVE LOGITS
     this
    1.36
    ↵↵↵↵↵
    1.30
    ↵↵↵
    1.27
    ↵↵↵↵
    1.24
    ↵↵↵↵↵↵↵
    1.19
    <eos>
    1.12
    ↵↵↵↵↵↵
    1.10
     этой
    1.08
    ↵↵↵↵↵↵↵↵
    1.03
     этого
    1.03
    Activations Density 0.140%

    No Known Activations