© 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. 92198
    Prev
    Next
    INDEX
    Explanations

    software license terms

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron flags software license header blocks, in particular lines with copyright/license metadata.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    Tác
    -0.98
     Thần
    -0.98
     Tiểu
    -0.97
    ">[
    -0.91
     Quý
    -0.90
     Máy
    -0.86
    ({
    -0.85
    lijken
    -0.85
     Quận
    -0.85
     Đình
    -0.84
    POSITIVE LOGITS
    TTC
    0.79
     Khan
    0.74
    ֶה
    0.73
     なく
    0.73
    checkpoint
    0.72
    Gx
    0.72
     yonder
    0.72
     Greensboro
    0.70
     empê
    0.70
     helyzet
    0.70
    Activations Density 0.001%

    No Known Activations