© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 83909
    Prev
    Next
    INDEX
    Explanations

    benefits and achievements

    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
     relev
    -0.79
     jPanel
    -0.78
    hore
    -0.78
    trone
    -0.78
    recommended
    -0.77
    ivel
    -0.77
    ämpfer
    -0.77
     policiais
    -0.75
    ſen
    -0.75
     зада
    -0.75
    POSITIVE LOGITS
     realized
    2.39
     realised
    1.99
     realization
    1.98
     achieved
    1.95
     realize
    1.87
     realizes
    1.82
     realisation
    1.79
     accrue
    1.74
     accrued
    1.68
     realizing
    1.67
    Activations Density 0.046%

    No Known Activations