© 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. 22-GEMMASCOPE-RES-131K
    7. 67151
    Prev
    Next
    INDEX
    Explanations

    focus on space and time

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

    This neuron detects action verbs that express freeing up, expanding, or enabling resources or capacity.

    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
    ādā
    -0.99
     SafeArea
    -0.92
     sustituir
    -0.91
     навіть
    -0.88
     Даже
    -0.87
     часов
    -0.86
    AndWait
    -0.85
     aceptar
    -0.85
     ölü
    -0.84
     justify
    -0.84
    POSITIVE LOGITS
     for
    1.41
     other
    1.40
     more
    1.27
     space
    1.12
     başka
    1.09
     elsewhere
    1.07
     focusing
    1.05
    concentr
    1.05
     focus
    1.00
     another
    0.98
    Activations Density 0.023%

    No Known Activations