© 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. 64890
    Prev
    Next
    INDEX
    Explanations

    stopping or stationary

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

    The neuron flags terms that indicate stopping or being motionless (e.g., stationary, idle, stopped, broke down).

    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
     båda
    -0.91
    iedy
    -0.88
    WW
    -0.87
     incluso
    -0.86
    sel
    -0.86
    le
    -0.84
    dia
    -0.84
     glisser
    -0.84
    ç
    -0.83
     assumption
    -0.83
    POSITIVE LOGITS
     on
    1.23
     at
    1.18
     waiting
    1.08
     wachten
    1.07
     near
    1.07
     parked
    1.02
     halt
    1.01
     bolí
    1.00
     filtros
    0.99
     wait
    0.98
    Activations Density 0.068%

    No Known Activations