© 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. 90494
    Prev
    Next
    INDEX
    Explanations

    this and

    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
     Bianca
    -0.72
     Recherches
    -0.71
    seth
    -0.71
     UTF
    -0.70
    uerst
    -0.69
    PERCENT
    -0.68
     Optimal
    -0.68
     Scope
    -0.68
    idc
    -0.67
    良
    -0.67
    POSITIVE LOGITS
     업
    0.69
    있
    0.67
     אלי
    0.67
    াপ
    0.64
    формация
    0.64
    знес
    0.64
     episódio
    0.63
     作業
    0.63
     tokenId
    0.62
    Replication
    0.62
    Activations Density 0.061%

    No Known Activations