© 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. 94149
    Prev
    Next
    INDEX
    Explanations

    over the past

    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
     νο
    -0.92
     above
    -0.90
     Լ
    -0.89
     别墅
    -0.89
    standes
    -0.87
     etui
    -0.84
     when
    -0.84
     Audits
    -0.81
    телна
    -0.81
     作成
    -0.80
    POSITIVE LOGITS
     the
    2.14
     recente
    1.13
    Recent
    1.05
     recent
    1.04
    recent
    1.03
     reciente
    1.02
     comportements
    0.93
     summer
    0.93
     pertes
    0.93
     afgelopen
    0.89
    Activations Density 0.020%

    No Known Activations