© 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. 59086
    Prev
    Next
    INDEX
    Explanations

    activity

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

    The neuron fires strongly on technical measurement terms and experimental condition parameters (e.g. water activity, temperature, incubation time) in scientific methodology descriptions.

    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
    鹫
    -0.86
     Shapiro
    -0.70
     прокура
    -0.69
     Assault
    -0.68
    tria
    -0.68
    eders
    -0.67
    VOLUME
    -0.67
    afka
    -0.66
    抿
    -0.66
    纪
    -0.66
    POSITIVE LOGITS
     activity
    1.37
     actividad
    1.29
     fug
    1.19
    activity
    1.15
     atividade
    1.13
     activities
    1.08
     Activity
    1.05
     activité
    1.05
    Fug
    1.05
    Activity
    1.02
    Activations Density 0.030%

    No Known Activations