© 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. 118559
    Prev
    Next
    INDEX
    Explanations

    ' and numbers

    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
    +")
    -0.76
    𝐟
    -0.75
     narcis
    -0.74
     őket
    -0.73
    enerbahçe
    -0.72
    shift
    -0.71
    est
    -0.71
     उन्ह
    -0.71
    dias
    -0.70
     nerv
    -0.69
    POSITIVE LOGITS
     –
    0.98
    ––––
    0.78
     –,
    0.75
    YK
    0.73
    izaciones
    0.71
     sofá
    0.71
    .–
    0.70
     \%-
    0.70
    etone
    0.70
     mẹ
    0.70
    Activations Density 0.143%

    No Known Activations