© 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. 73642
    Prev
    Next
    INDEX
    Explanations

    deposit in accounts or casinos

    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
    1
    -1.31
    IN
    -1.20
    8
    -1.08
    7
    -1.05
    4
    -1.00
     Brought
    -0.98
     действий
    -0.98
    地上
    -0.98
    6
    -0.98
    2
    -0.96
    POSITIVE LOGITS
    欧盟
    1.06
    landaise
    1.02
     umowy
    0.99
     mobilization
    0.96
    ꯷
    0.96
    罔
    0.95
    ksz
    0.94
     abandonar
    0.94
     armas
    0.93
    嬗
    0.93
    Activations Density 0.006%

    No Known Activations