© 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. 12260
    Prev
    Next
    INDEX
    Explanations

    names of people and acronyms

    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
    s
    -3.16
    3
    -3.11
    2
    -3.03
    4
    -2.95
    '
    -2.78
    ⏑
    -2.78
     Veränder
    -2.77
    }
    -2.72
     approaching
    -2.67
     geprü
    -2.64
    POSITIVE LOGITS
    and
    3.41
    琑
    2.89
    狁
    2.67
    𝐒
    2.58
    🌹
    2.55
    🍀
    2.53
    栳
    2.48
     и
    2.48
    ()?
    2.47
    热水
    2.39
    Activations Density 0.009%

    No Known Activations