© 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. 34-GEMMASCOPE-RES-131K
    7. 93655
    Prev
    Next
    INDEX
    Explanations

    segues and transitions

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

    The neuron fires strongly on low‐frequency or unusually rare tokens (including uncommon words and code/identifier fragments).

    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
     ফ
    -0.84
    を目指
    -0.81
     awakeFromNib
    -0.80
    heits
    -0.79
    addContainerGap
    -0.79
    become
    -0.77
    пер
    -0.76
    verwaltung
    -0.76
     COMMUNICATION
    -0.75
     firft
    -0.74
    POSITIVE LOGITS
     segue
    3.17
     transition
    3.06
     transitions
    2.53
    transition
    2.41
     transitioning
    2.39
    Transition
    2.39
     Transition
    2.34
     transitioned
    2.31
     Transitions
    2.25
     seg
    2.22
    Activations Density 0.024%

    No Known Activations