© 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. 128278
    Prev
    Next
    INDEX
    Explanations

    amusement park rides

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

    The neuron flags mentions of amusement-park attractions (rides, slides, coasters, etc.).

    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
    няется
    -1.22
     December
    -1.19
     înal
    -1.17
    oustic
    -1.16
    th
    -1.12
     frumos
    -1.12
    gitto
    -1.11
     між
    -1.09
     your
    -1.08
     Continuing
    -1.07
    POSITIVE LOGITS
    ꜆
    1.34
     also
    1.27
     sindic
    1.26
    --}}
    1.24
     straff
    1.23
     expérience
    1.22
    맑
    1.21
    ꩜
    1.20
     abrir
    1.20
     høre
    1.18
    Activations Density 0.022%

    No Known Activations