© 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. 10-GEMMASCOPE-RES-131K
    7. 19505
    Prev
    Next
    INDEX
    Explanations

    context of problems

    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_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
    REDIT
    -1.80
    旆
    -1.76
    }$.
    -1.71
     the
    -1.71
    lorum
    -1.65
    )=\
    -1.64
    mlung
    -1.63
    는
    -1.63
    ātu
    -1.63
    !
    -1.63
    POSITIVE LOGITS
     Also
    2.05
     или
    1.95
     красивые
    1.93
     problemas
    1.91
    或者
    1.89
     gracios
    1.88
    Also
    1.87
    或
    1.86
     sentito
    1.85
     швидко
    1.84
    Activations Density 0.135%

    No Known Activations