© 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. 118505
    Prev
    Next
    INDEX
    Explanations

    code includes and system headers

    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
    GAC
    -0.81
     Separ
    -0.76
    ฉัน
    -0.74
     counselor
    -0.73
     Mendes
    -0.72
    Separ
    -0.72
     совет
    -0.71
     alors
    -0.71
    OrderItem
    -0.71
     créer
    -0.71
    POSITIVE LOGITS
     SPDX
    0.79
     enthusiasts
    0.78
    nienie
    0.77
    .=
    0.74
    Potion
    0.73
    Nossa
    0.72
    ніципа
    0.72
     Wanda
    0.72
     methylene
    0.71
     inau
    0.71
    Activations Density 0.086%

    No Known Activations