© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 58907
    Prev
    Next
    INDEX
    Explanations

    MIT license

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

    The neuron detects mentions of the MIT license (e.g. occurrences of “MIT License” or “LICENSE” in header blocks).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    '
    -2.48
    al
    -2.41
     
    -2.36
    en
    -2.27
    ࿚
    -2.20
    家伙
    -2.17
    ꔹ
    -2.17
    on
    -2.17
    इटम
    -2.09
    𖤣
    -2.08
    POSITIVE LOGITS
     في
    2.41
     в
    2.41
    喈
    2.34
    皤
    2.31
     brukt
    2.31
     sikkert
    2.30
    s
    2.23
     abbreviated
    2.20
    酲
    2.19
    FormTagHelper
    2.17
    Activations Density 0.014%

    No Known Activations