© 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. 10-GEMMASCOPE-RES-131K
    4. 123711
    Prev
    Next
    INDEX
    Explanations

    limited or limitation

    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
     Вес
    -2.23
     Añade
    -2.13
    栳
    -2.11
     Agrega
    -1.99
     帳
    -1.98
     lunghi
    -1.95
    都想
    -1.93
    괌
    -1.93
     Resultat
    -1.92
     bewertet
    -1.91
    POSITIVE LOGITS
    the
    3.11
    ’
    3.05
    m
    2.81
    ),
    2.81
    ).
    2.80
    ↵
    2.77
    稣
    2.58
    鸲
    2.52
    </strong>
    2.48
    in
    2.39
    Activations Density 0.041%

    No Known Activations