© 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. 83095
    Prev
    Next
    INDEX
    Explanations

    to support

    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
     use
    -1.35
     finds
    -1.16
     being
    -1.13
     providing
    -1.08
     offering
    -1.05
     blanco
    -1.05
    用
    -1.05
     become
    -1.04
     assigning
    -1.03
     allow
    -1.02
    POSITIVE LOGITS
    😲
    1.06
    💌
    0.99
    🏅
    0.97
     zijne
    0.94
    chartInstance
    0.93
    journalist
    0.93
     découv
    0.92
    +'/
    0.91
    \!
    0.91
    ごとの
    0.91
    Activations Density 0.404%

    No Known Activations