© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 77296
    Prev
    Next
    INDEX
    Explanations

    code separators or delimiters

    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
    感じで
    -0.86
     setempat
    -0.84
     mempel
    -0.82
     terdekat
    -0.79
     Alemanha
    -0.74
     günstig
    -0.74
     diduga
    -0.73
    ᵇ
    -0.73
     Ꮎ
    -0.73
     this
    -0.73
    POSITIVE LOGITS
     یا
    0.89
     vân
    0.86
    ENDENT
    0.86
    ioms
    0.86
    setViewName
    0.85
     потому
    0.85
    さらに
    0.84
    是怎么回事
    0.82
     또
    0.82
     také
    0.82
    Activations Density 0.116%

    No Known Activations