© 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. 92098
    Prev
    Next
    INDEX
    Explanations

    code comments and documentation

    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
     your
    -0.98
     and
    -0.94
     glorious
    -0.93
     flawless
    -0.91
     countless
    -0.90
    -
    -0.88
     prachtig
    -0.87
    렸
    -0.87
     too
    -0.86
    Breathing
    -0.85
    POSITIVE LOGITS
    kiwa
    0.99
     {@
    0.94
     Ο
    0.93
    adhyay
    0.93
    paku
    0.92
    OOT
    0.92
    WAII
    0.91
    ută
    0.91
    rya
    0.91
    vae
    0.90
    Activations Density 0.010%

    No Known Activations