© 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. 58993
    Prev
    Next
    INDEX
    Explanations

    marvel, avengers, infinity

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

    This neuron is essentially inactive—it does not reliably activate on any tokens.

    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
    s
    -3.39
    琑
    -3.02
     ‘
    -2.83
    ᕮ
    -2.61
    ſſel
    -2.47
    嘥
    -2.39
    䜣
    -2.39
    crapers
    -2.30
     április
    -2.23
     (‘
    -2.19
    POSITIVE LOGITS
    ).
    3.09
    .'
    3.02
    .''
    2.86
    .\\
    2.55
    ↵
    2.41
    \\
    2.39
    ～～～～
    2.34
    _{
    2.31
    酲
    2.30
    .")
    2.27
    Activations Density 0.021%

    No Known Activations