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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 100648
    Prev
    Next
    INDEX
    Explanations

    hexadecimal constants

    np_acts-logits-general · gemini-2.5-flash-lite

    hexadecimal numbers (typically following "0x" notation in code).

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     aktivitet
    -2.30
    is
    -2.23
     has
    -2.16
    y
    -2.16
    剎
    -2.08
    ⑊
    -2.06
    e
    -2.00
     with
    -1.96
    їна
    -1.95
    )
    
    -1.95
    POSITIVE LOGITS
    ↵
    2.36
     Beſ
    2.28
     mereka
    2.23
    CurtirCurtir
    2.17
    媄
    2.08
    Ингредиенты
    2.00
    :
    2.00
     كانوا
    1.97
     Belakang
    1.95
    Зно
    1.88
    Activations Density 0.010%

    No Known Activations