© 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. 86946
    Prev
    Next
    INDEX
    Explanations

    crime and convictions

    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
    лев
    -0.82
     slightly
    -0.81
     editText
    -0.80
     leves
    -0.78
    ậc
    -0.76
    лку
    -0.76
     PRESENTED
    -0.76
    Usual
    -0.75
    送信
    -0.75
    ən
    -0.75
    POSITIVE LOGITS
     felony
    1.22
     любого
    1.17
     anywhere
    1.13
     qualsiasi
    1.11
     ANY
    1.05
     any
    1.02
    任何
    0.99
     Fel
    0.95
     cualquier
    0.94
    曾
    0.92
    Activations Density 0.022%

    No Known Activations