© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 12379
    Prev
    Next
    INDEX
    Explanations

    numeric sequences and special characters

    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_22/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
     only
    -1.48
     on
    -1.45
     make
    -1.18
     from
    -1.14
     when
    -1.02
     people
    -1.02
     two
    -1.01
     única
    -1.00
     .....
    -1.00
     with
    -0.98
    POSITIVE LOGITS
    Tür
    1.07
    
    1.05
     unei
    1.04
     ilgili
    1.02
     mojej
    1.02
    omio
    1.02
    你先
    1.02
    jeuner
    1.01
     蔬菜
    1.00
     批量
    1.00
    Activations Density 0.002%

    No Known Activations