© 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. 34505
    Prev
    Next
    INDEX
    Explanations

    php, Q, [, Serum

    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
     feelings
    -1.15
     programs
    -1.00
     emotions
    -0.89
    feelings
    -0.89
     Feelings
    -0.88
     Program
    -0.80
    Programs
    -0.77
     PROGRAMS
    -0.76
     Programs
    -0.74
    ưỡi
    -0.74
    POSITIVE LOGITS
    Ｈ
    0.96
    ueil
    0.85
    dll
    0.79
    selected
    0.79
     ailleurs
    0.77
    辋
    0.73
    Memorial
    0.73
     голо
    0.72
    HOT
    0.72
    quel
    0.71
    Activations Density 0.023%

    No Known Activations