© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 3231
    Prev
    Next
    INDEX
    Explanations

    phone numbers with 4

    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
     they
    -0.91
    towych
    -0.87
    泓
    -0.84
     Oberfläche
    -0.82
     ville
    -0.81
     žena
    -0.81
    በ
    -0.81
    extends
    -0.78
     povr
    -0.78
    слож
    -0.78
    POSITIVE LOGITS
    ⅜
    0.79
    )};
    0.77
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.74
    ksu
    0.74
    టు
    0.73
    כים
    0.72
    ㈧
    0.72
     quelque
    0.71
    真剣
    0.71
     ショルダー
    0.71
    Activations Density 0.007%

    No Known Activations