© 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. 77831
    Prev
    Next
    INDEX
    Explanations

    words ending in -um or -lum

    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
    避難
    -0.75
    eln
    -0.73
    UTUP
    -0.68
     websites
    -0.68
     descriptions
    -0.66
     Treffen
    -0.66
    囤
    -0.66
     risk
    -0.66
     culprits
    -0.65
     others
    -0.65
    POSITIVE LOGITS
    тора
    0.87
    tum
    0.85
    mers
    0.79
    Ќ
    0.78
    bral
    0.77
    BERTO
    0.77
    Extract
    0.76
    son
    0.76
    Dataset
    0.75
    sum
    0.75
    Activations Density 0.057%

    No Known Activations