© 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. 92504
    Prev
    Next
    INDEX
    Explanations

    copyright, trademark, license, terms

    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
    PRESSION
    -0.75
    AndroidJUnit
    -0.72
    therosclerosis
    -0.71
    lw
    -0.71
    ȫ
    -0.70
    Nota
    -0.69
     Leave
    -0.68
    inosa
    -0.66
     createStore
    -0.66
     strada
    -0.66
    POSITIVE LOGITS
    Ultimate
    1.07
     ultimate
    1.05
    ultimate
    0.96
     Ultimate
    0.94
     ulti
    0.77
     Hund
    0.74
     supreme
    0.66
    alet
    0.66
    ULT
    0.63
    tuck
    0.63
    Activations Density 0.060%

    No Known Activations