© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 91948
    Prev
    Next
    INDEX
    Explanations

    critical or crt sequences

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

    The neuron fires on tokens containing the consonant cluster “crt” (in order), e.g. in gene names like crtZ/ctrW and in words like Crit, Cretaceous, Crato, Crataegus, criteria, 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_34/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
     ]}
    -0.85
    haji
    -0.83
    grip
    -0.75
     Grip
    -0.74
     zis
    -0.73
    ked
    -0.72
    physics
    -0.72
    kkk
    -0.71
    seye
    -0.71
    Przeczytaj
    -0.71
    POSITIVE LOGITS
    EClass
    0.71
    idr
    0.66
    优化
    0.66
     행
    0.65
     crit
    0.64
    使用者
    0.64
     angka
    0.62
    woll
    0.62
    というのが
    0.62
     poorest
    0.60
    Activations Density 0.027%

    No Known Activations