© 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. 22-GEMMASCOPE-RES-131K
    7. 65124
    Prev
    Next
    INDEX
    Explanations

    word endings

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

    The neuron consistently lights up on longer, multi‐syllable technical or scientific terms—i.e. unusually long specialist words.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     well
    -1.12
     stated
    -1.04
     an
    -1.04
     kept
    -1.03
     様
    -1.02
     &
    -1.02
     soo
    -1.01
     first
    -1.00
     is
    -0.98
    问题
    -0.97
    POSITIVE LOGITS
    aient
    1.32
    
    1.16
    uteurs
    1.13
     xvii
    1.10
     lateinit
    1.10
    collider
    1.10
    «,
    1.09
     devenus
    1.08
     dátum
    1.08
    hawatir
    1.07
    Activations Density 0.008%

    No Known Activations