© 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. 639
    Prev
    Next
    INDEX
    Explanations

    mathematical context

    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
     default
    -0.83
     spite
    -0.77
     shut
    -0.76
    OrFail
    -0.75
    boe
    -0.75
    ₆
    -0.74
    ゲート
    -0.73
    cdonald
    -0.73
    ungu
    -0.72
     بیشتر
    -0.71
    POSITIVE LOGITS
    "،
    0.92
    Struktur
    0.82
    cycline
    0.82
    pptx
    0.79
    leri
    0.78
    yczny
    0.78
     fangs
    0.77
    mittags
    0.76
    digd
    0.76
    riert
    0.75
    Activations Density 0.008%

    No Known Activations